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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     presentation
    -0.06
    >"+
    -0.06
     Hew
    -0.06
     show
    -0.06
    	display
    -0.06
     MatSnackBar
    -0.06
    める
    -0.06
    cite
    -0.06
    (Action
    -0.06
    .ham
    -0.06
    POSITIVE LOGITS
    ว
    0.08
     rủi
    0.07
     �
    0.07
    玩
    0.06
    ording
    0.06
    契
    0.06
     νεφοκ
    0.06
     خیلی
    0.06
    睡
    0.06
     مجلس
    0.06
    Act Density 0.003%

    No Known Activations