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

    Neuronpedia

    INDEX
    Explanations

    guilty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dez
    -0.06
    likelihood
    -0.06
     떠
    -0.06
     Сп
    -0.06
    _USART
    -0.06
    PR
    -0.06
    !.
    -0.06
     مس
    -0.06
    Splash
    -0.06
    reffen
    -0.06
    POSITIVE LOGITS
     guilty
    0.07
    Application
    0.07
     Distribution
    0.07
    Certificate
    0.06
    _intersect
    0.06
     información
    0.06
     discovered
    0.06
    ğinde
    0.06
     gastrointestinal
    0.06
    根
    0.06
    Act Density 0.003%

    No Known Activations