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

    Neuronpedia

    INDEX
    Explanations

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дис
    -0.07
    FM
    -0.07
    %c
    -0.07
     Guth
    -0.06
    _DF
    -0.06
    TF
    -0.06
    WIN
    -0.06
    ingen
    -0.06
    _ins
    -0.06
    produto
    -0.06
    POSITIVE LOGITS
     better
    0.07
     happier
    0.07
    @"↵
    0.07
     more
    0.07
     ligne
    0.07
     easier
    0.07
     Better
    0.06
    (connectionString
    0.06
     رفع
    0.06
    んと
    0.06
    Act Density 0.178%

    No Known Activations