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

    Neuronpedia

    INDEX
    Explanations

    Unusual characters/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Au
    -0.07
    保護
    -0.07
     pee
    -0.07
    trait
    -0.06
    _LABEL
    -0.06
     に
    -0.06
     listItem
    -0.06
    aversable
    -0.06
    Activ
    -0.06
     environ
    -0.06
    POSITIVE LOGITS
    igits
    0.07
     Redskins
    0.06
     Tradition
    0.06
    理由
    0.06
    ického
    0.06
    %;"
    0.06
     scattered
    0.06
    /unit
    0.06
    0.06
    ifferent
    0.06
    Act Density 0.091%

    No Known Activations