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

    Neuronpedia

    INDEX
    Explanations

    Code with "Len", "amily"

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literals (tokens containing digits) in the source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tắt
    -0.07
    аша
    -0.06
    تهم
    -0.06
    ウト
    -0.06
     shores
    -0.06
    Tracks
    -0.06
    clist
    -0.06
     원
    -0.06
    rain
    -0.06
     Indo
    -0.06
    POSITIVE LOGITS
    /h
    0.08
     theological
    0.07
     второй
    0.07
    RootElement
    0.07
     Butterfly
    0.06
    .DateTimeField
    0.06
    зация
    0.06
    ویزی
    0.06
    j
    0.06
     με
    0.06
    Act Density 0.001%

    No Known Activations