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

    Neuronpedia

    INDEX
    Explanations

    -based and -driven

    np_max-act · gemini-2.0-flash

    content related to structuring and managing tasks or workflows within software applications.

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

    This neuron never activates on any input tokens, so it does not detect or respond to any particular text pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    x
    -0.06
     eleven
    -0.06
     LIMITED
    -0.06
     Cathedral
    -0.06
     Apprentice
    -0.06
    <source
    -0.06
     apprentice
    -0.06
    .Registry
    -0.06
    .Zero
    -0.06
    .nano
    -0.06
    POSITIVE LOGITS
    -based
    0.08
    sız
    0.08
     Used
    0.07
    鼻
    0.07
    었
    0.07
    -Based
    0.07
    처
    0.07
     used
    0.07
     اندازه
    0.07
     нельзя
    0.07
    Act Density 0.024%

    No Known Activations