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

    Neuronpedia

    INDEX
    Explanations

    occurrences of parentheses and dollar signs, indicating expressions or variables

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

    Weil divisor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ciudadana
    -0.38
     literaria
    -0.34
     inspiradoras
    -0.33
     productivo
    -0.32
     Plenum
    -0.32
     nødven
    -0.32
     ancha
    -0.32
     electrónica
    -0.32
     norsk
    -0.31
     finnes
    -0.31
    POSITIVE LOGITS
    awtextra
    0.91
    下载附件
    0.90
    IntoConstraints
    0.85
    uxxxx
    0.85
    ьаж
    0.83
    httphttps
    0.81
    GEBURTSDATUM
    0.81
     виправивши
    0.81
     незавершена
    0.80
    GEBURTS
    0.80
    Act Density 0.002%

    No Known Activations