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

    Neuronpedia

    INDEX
    Explanations

    mentions of column classes in a code or markup context

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

    sql column names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infór
    -0.40
    ſelves
    -0.40
     probado
    -0.39
     temprano
    -0.37
     araña
    -0.37
    ſelf
    -0.36
    GTCX
    -0.36
     naturelle
    -0.35
     przysz
    -0.35
     présidenti
    -0.35
    POSITIVE LOGITS
    col
    2.17
     col
    1.77
    Col
    1.67
     Col
    1.61
    COL
    1.38
     COL
    1.33
    cols
    1.14
     cols
    1.13
    Cols
    1.08
     kol
    1.02
    Act Density 0.001%

    No Known Activations