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

    Neuronpedia

    INDEX
    Explanations

    numerical computation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lov
    -0.09
    Lov
    -0.08
     Lov
    -0.08
    കാര
    -0.08
    дар
    -0.08
     גם
    -0.08
    Permission
    -0.07
    .background
    -0.07
     Karn
    -0.07
     त्यांच्या
    -0.07
    POSITIVE LOGITS
     wp
    0.08
     bb
    0.08
     collectivités
    0.08
     barely
    0.08
     brim
    0.07
     Reson
    0.07
     bp
    0.07
     xwb
    0.07
     ছোট
    0.07
     insignificant
    0.07
    Act Density 0.061%

    No Known Activations