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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    This neuron responds most to longer (less frequent) tokens, with activation roughly increasing as token length increases.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    نده
    -0.07
    _clause
    -0.07
    À
    -0.06
     устрой
    -0.06
    .getLeft
    -0.06
     Jung
    -0.06
     Christ
    -0.06
     реак
    -0.06
    _PROCESS
    -0.06
    оком
    -0.06
    POSITIVE LOGITS
    -specific
    0.07
     exports
    0.07
     relaciones
    0.06
     backgroundColor
    0.06
     genetically
    0.06
     یا
    0.06
     overse
    0.06
    ğını
    0.06
     Ό
    0.06
    backgroundColor
    0.06
    Act Density 0.000%

    No Known Activations