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

    Neuronpedia

    INDEX
    Explanations

    say "able"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sert
    -0.06
     obligated
    -0.06
    281
    -0.06
    hor
    -0.06
     全
    -0.06
     tuning
    -0.06
    589
    -0.06
     Translator
    -0.06
     слід
    -0.06
    ＊
    -0.05
    POSITIVE LOGITS
    ToObject
    0.07
     č
    0.07
    ricia
    0.07
    .POS
    0.07
     YELLOW
    0.07
     kích
    0.06
    .GetService
    0.06
     Pom
    0.06
     kullanıcı
    0.06
     जनत
    0.06
    Act Density 0.056%

    No Known Activations