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

    Neuronpedia

    INDEX
    Explanations

    instructions or advice

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that appear in step-by-step troubleshooting or instructional sentences, especially the common words and verbs used in numbered how-to guidance.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     projector
    -0.08
    Constant
    -0.07
    icles
    -0.07
    ursors
    -0.07
    alted
    -0.07
    (___
    -0.06
     microscopy
    -0.06
     nord
    -0.06
    antically
    -0.06
    olecular
    -0.06
    POSITIVE LOGITS
     tady
    0.07
    wind
    0.07
     trom
    0.06
     исключ
    0.06
     archivo
    0.06
    ocation
    0.06
    hill
    0.06
     UIGraphics
    0.06
    ville
    0.06
    때
    0.06
    Act Density 0.055%

    No Known Activations