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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attacker
    -0.08
     ölüm
    -0.07
     physique
    -0.07
    τεύ
    -0.06
     environment
    -0.06
     partially
    -0.06
     rims
    -0.06
     jud
    -0.06
     trolling
    -0.06
    .Normalize
    -0.06
    POSITIVE LOGITS
    .VarChar
    0.06
    context
    0.06
    ContentPane
    0.06
     asyncio
    0.06
    (super
    0.06
    poss
    0.06
     recursive
    0.06
    58
    0.06
    ını
    0.06
    dbh
    0.06
    Act Density 0.002%

    No Known Activations