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

    Neuronpedia

    INDEX
    Explanations

    Non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lac
    -0.07
     kval
    -0.07
    gd
    -0.07
     ambiente
    -0.07
    __
↵
    -0.06
    。↵↵
    -0.06
     Clarke
    -0.06
     المو
    -0.06
     Titan
    -0.06
     Advantage
    -0.06
    POSITIVE LOGITS
     मत
    0.06
     голову
    0.06
    LEFT
    0.06
    $PostalCodesNL
    0.06
    长度
    0.06
     наук
    0.06
    左右
    0.06
    UPER
    0.06
    werp
    0.06
    .embed
    0.06
    Act Density 0.058%

    No Known Activations