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

    Neuronpedia

    INDEX
    Explanations

    Minist

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     боли
    -0.06
    тов
    -0.06
     Бог
    -0.06
    KT
    -0.06
    larla
    -0.06
    conversion
    -0.06
    Conversion
    -0.06
    440
    -0.06
    Conn
    -0.06
    POSITIVE LOGITS
    uma
    0.07
    /wait
    0.07
    -monitor
    0.07
     sexkontakte
    0.06
     choke
    0.06
    .strip
    0.06
     syncing
    0.06
     applauded
    0.06
    _Word
    0.06
     enjoy
    0.06
    Act Density 0.002%

    No Known Activations