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

    Neuronpedia

    INDEX
    Explanations

    ongoing changes or progress indicated by statistical data and comparisons over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    change or progress

    np_acts-logits-general · gemini-2.0-flash

    increase since

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     endregion
    -0.55
     nonatomic
    -0.54
    enderal
    -0.54
     begins
    -0.52
    wsdl
    -0.51
    startswith
    -0.51
    ambilan
    -0.46
    PrototypeOf
    -0.45
    Weiterlesen
    -0.45
     лай
    -0.45
    POSITIVE LOGITS
     since
    1.20
     SINCE
    1.09
    since
    1.09
     depuis
    1.08
    Since
    0.96
    Depuis
    0.94
     fince
    0.93
     Since
    0.91
    depuis
    0.86
     Depuis
    0.82
    Act Density 0.336%

    No Known Activations