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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -0.67
     său
    -0.57
    ,‎
    -0.55
    FromNib
    -0.53
     auffi
    -0.53
     Efq
    -0.51
     <",
    -0.50
     againſt
    -0.50
    ]")]
    -0.50
     ویکی‌پدیای
    -0.49
    POSITIVE LOGITS
     the
    0.65
    ophanes
    0.60
     Gross
    0.58
     AG
    0.58
    gross
    0.57
     Gar
    0.56
    link
    0.56
    gro
    0.55
    uba
    0.55
    priority
    0.55
    Act Density 0.238%

    No Known Activations