Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    lack of awareness

    np_max-act · gemini-2.0-flash

    text related to digital content creation and its potential implications, particularly concerning artificial intelligence.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on words and phrases signaling knowledge or the ability to discern—especially instances of “know,” “tell,” or similar epistemic/differentiation cues.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     můž
    -0.06
     собі
    -0.06
     onSuccess
    -0.06
    (Player
    -0.06
    ่
    -0.06
     válido
    -0.06
    (delay
    -0.06
     важ
    -0.06
     účet
    -0.06
     timely
    -0.06
    POSITIVE LOGITS
    .FileSystem
    0.07
    .CopyTo
    0.06
     splitter
    0.06
    /cm
    0.06
    Observer
    0.06
    041
    0.06
     cov
    0.06
     Strategic
    0.06
     був
    0.06
     FileSystem
    0.06
    Act Density 0.011%

    No Known Activations