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
    excel
    -0.07
    ueblo
    -0.07
    663
    -0.07
    zap
    -0.07
    @NoArgsConstructor
    -0.07
    -ret
    -0.06
    .popup
    -0.06
    trained
    -0.06
     estates
    -0.06
    coins
    -0.06
    POSITIVE LOGITS
    .drawText
    0.07
     какие
    0.07
     SYMBOL
    0.06
    (Environment
    0.06
     Мал
    0.06
    <Value
    0.06
    ());↵↵↵
    0.06
    140
    0.06
     statistically
    0.06
     доп
    0.06
    Act Density 0.011%

    No Known Activations