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

    Neuronpedia

    INDEX
    Explanations

    forfeitures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     condominium
    -0.07
    깐
    -0.07
    .feedback
    -0.07
    ˬ
    -0.07
    蒗
    -0.07
    的优点
    -0.07
     yardı
    -0.07
     Nationwide
    -0.07
    鳑
    -0.07
    敝
    -0.07
    POSITIVE LOGITS
    Level
    0.08
    target
    0.07
    	Task
    0.07
     tab
    0.07
    澳洲
    0.07
    Recipient
    0.07
     Hearing
    0.07
    체
    0.07
    直播
    0.07
    _dept
    0.07
    Act Density 0.013%

    No Known Activations