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

    Neuronpedia

    INDEX
    Explanations

    code/mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    laps
    -0.08
    looking
    -0.08
    _CONT
    -0.08
     дня
    -0.08
    uft
    -0.07
    sample
    -0.07
    ochastic
    -0.07
    Variation
    -0.07
    Loop
    -0.07
    oblast
    -0.07
    POSITIVE LOGITS
     Cheer
    0.09
     Batt
    0.08
     hustle
    0.08
     additive
    0.08
     Cheats
    0.08
     afzonder
    0.08
    фикация
    0.08
     Invent
    0.08
     Бо
    0.08
     conquista
    0.07
    Act Density 0.047%

    No Known Activations