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

    Neuronpedia

    INDEX
    Explanations

    Non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лиц
    -0.08
    손
    -0.06
     læ
    -0.06
     horsepower
    -0.06
    저
    -0.06
    lač
    -0.06
    ої
    -0.06
    _FRAME
    -0.06
    픽
    -0.06
     infile
    -0.06
    POSITIVE LOGITS
     Healing
    0.07
     bele
    0.07
     servings
    0.07
     imageURL
    0.06
     SEM
    0.06
     magical
    0.06
    iyat
    0.06
     природ
    0.06
    ,password
    0.06
     extraction
    0.06
    Act Density 0.001%

    No Known Activations