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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the substring “edit,” for example in icon names like “glyphicon-edit.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    hey
    -0.07
    periments
    -0.07
    816
    -0.06
    _kwargs
    -0.06
     Bis
    -0.06
     Academic
    -0.06
    596
    -0.06
    pole
    -0.06
     ظ
    -0.06
    ैक
    -0.06
    POSITIVE LOGITS
    [(
    0.07
    \">"
    0.07
     التج
    0.07
     argc
    0.07
    (rawValue
    0.07
    triangle
    0.07
     разм
    0.07
     čist
    0.07
    ません
    0.06
    +self
    0.06
    Act Density 0.171%

    No Known Activations