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

    Neuronpedia

    INDEX
    Explanations

    Numerical calculations and differences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zbollah
    -0.08
     மேலும்
    -0.08
    ازت
    -0.08
     ხოლო
    -0.07
     Filename
    -0.07
     clicking
    -0.07
    bookmark
    -0.07
    َّ
    -0.07
    production
    -0.07
     Production
    -0.07
    POSITIVE LOGITS
    .settings
    0.08
     minor
    0.07
    Moved
    0.07
    隔
    0.07
    ಿಲ್ಲ
    0.07
     kroppen
    0.07
    .delta
    0.07
    ನ್ನು
    0.07
    .reason
    0.07
     dosis
    0.07
    Act Density 0.074%

    No Known Activations