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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LOGIN
    -0.07
     locate
    -0.06
     interface
    -0.06
     Unique
    -0.06
    =$((
    -0.06
     thrust
    -0.06
     Error
    -0.05
     cosine
    -0.05
     Weapon
    -0.05
    Monad
    -0.05
    POSITIVE LOGITS
    xEF
    0.07
    家
    0.07
     tuned
    0.07
     apa
    0.07
    .simpleButton
    0.06
    Anything
    0.06
     onAnimation
    0.06
     Laur
    0.06
     liv
    0.06
    ensburg
    0.06
    Act Density 0.001%

    No Known Activations

    This feature has no known activations.