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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric literal tokens (numbers or number-like strings) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    えて
    -0.07
     QList
    -0.06
     grd
    -0.06
     dei
    -0.06
    이라는
    -0.06
     easiest
    -0.06
     �
    -0.06
    aec
    -0.06
    択
    -0.06
    _Last
    -0.06
    POSITIVE LOGITS
     vitality
    0.06
    .Byte
    0.06
     Personally
    0.06
     Savage
    0.06
     алког
    0.06
    TRANSFER
    0.06
     století
    0.06
     Spike
    0.06
    販売
    0.06
    .submit
    0.06
    Act Density 0.142%

    No Known Activations