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

    Neuronpedia

    INDEX
    Explanations

    computer code/commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Democratic
    -0.07
    ительные
    -0.07
     sword
    -0.07
    /game
    -0.07
     Shapiro
    -0.06
     sobie
    -0.06
     residues
    -0.06
     Numero
    -0.06
    andum
    -0.06
    seudo
    -0.06
    POSITIVE LOGITS
    ')");↵
    0.07
    �
    0.06
     جوان
    0.05
    $_['
    0.05
     وع
    0.05
    aut
    0.05
     Поч
    0.05
     temiz
    0.05
    цик
    0.05
    译
    0.05
    Act Density 0.015%

    No Known Activations