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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [-]:
    -0.06
     podmínek
    -0.06
    Reg
    -0.06
     yararlan
    -0.06
     ",↵
    -0.06
     Levy
    -0.06
    //{↵
    -0.06
     problémy
    -0.06
     ladder
    -0.06
    ,↵
    -0.06
    POSITIVE LOGITS
    flex
    0.07
     initialize
    0.07
    ît
    0.06
     gigg
    0.06
    лав
    0.06
     directors
    0.06
     TIME
    0.06
     conform
    0.06
    _atts
    0.06
    ologie
    0.06
    Act Density 0.109%

    No Known Activations