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

    Neuronpedia

    INDEX
    Explanations

    param

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    on
    -0.07
     Bull
    -0.07
    Actor
    -0.07
    тал
    -0.06
     годы
    -0.06
    Tiny
    -0.06
     Eggs
    -0.06
     Solomon
    -0.06
     HOT
    -0.06
     Flat
    -0.06
    POSITIVE LOGITS
    ベ
    0.07
    .Receive
    0.06
     toplam
    0.06
     tedav
    0.06
    เบ
    0.06
    (delete
    0.06
    gien
    0.06
    (DEBUG
    0.06
    pressions
    0.06
    character
    0.06
    Act Density 0.001%

    No Known Activations