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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    flutter
    -0.07
    splash
    -0.07
     здоровья
    -0.07
    $error
    -0.07
    WIN
    -0.07
     عليه
    -0.07
    contro
    -0.07
    厚度
    -0.07
    삭
    -0.06
    主角
    -0.06
    POSITIVE LOGITS
     Power
    0.07
    �
    0.07
    Partition
    0.07
    ']),↵
    0.06
     prv
    0.06
    +t
    0.06
     ax
    0.06
     Peer
    0.06
    .getFirst
    0.06
    高出
    0.06
    Act Density 0.009%

    No Known Activations