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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash

    The neuron fires on conditional‐logic keywords and operators (e.g. else, not, in) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Imports
    -0.08
     dataList
    -0.07
    علوم
    -0.07
    995
    -0.07
    iterals
    -0.06
    ("").
    -0.06
    .obs
    -0.06
     Women
    -0.06
    LogLevel
    -0.06
    exclude
    -0.06
    POSITIVE LOGITS
     sene
    0.06
     contenu
    0.06
    駆
    0.06
     forearm
    0.06
    초
    0.06
     kabul
    0.06
     Electoral
    0.06
    窗
    0.06
    AI
    0.06
     الغ
    0.06
    Act Density 0.024%

    No Known Activations