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

    Neuronpedia

    INDEX
    Explanations

    code and debugging

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of the “max” function (calls to max(), or discussion of getting the maximum value) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Charger
    -0.07
     Sok
    -0.06
     Hoffman
    -0.06
     Challenge
    -0.06
    .writeValue
    -0.06
    DITION
    -0.06
     обмеж
    -0.06
     '\\
    -0.06
    	of
    -0.06
     بنابر
    -0.06
    POSITIVE LOGITS
    .FindGameObjectWithTag
    0.06
    firstname
    0.06
     datové
    0.06
     ｌ
    0.06
    lou
    0.06
     currentState
    0.06
    ATYPE
    0.06
    _walk
    0.06
    ώντας
    0.06
    ındır
    0.06
    Act Density 0.116%

    No Known Activations