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

    Neuronpedia

    INDEX
    Explanations

    standardized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     score
    -1.41
    score
    -1.34
     Score
    -1.09
    Score
    -1.08
     scores
    -1.02
    scores
    -0.92
     USDA
    -0.90
     standardized
    -0.83
     Scores
    -0.80
    スコア
    -0.74
    POSITIVE LOGITS
    ########.
    0.86
    psack
    0.68
     continúas
    0.67
    BindView
    0.65
    expandindo
    0.65
     Siga
    0.63
    #+#
    0.62
    zzleHttp
    0.62
    NameInMap
    0.59
     wikipagina
    0.58
    Act Density 0.127%

    No Known Activations