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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OUT
    -0.07
    rive
    -0.07
     unlocking
    -0.07
    准入
    -0.07
     Ready
    -0.07
    rena
    -0.07
     markdown
    -0.07
    /member
    -0.07
    revolution
    -0.06
    UDIO
    -0.06
    POSITIVE LOGITS
    בלה
    0.07
     длительн
    0.07
     합니다
    0.07
    统计数据
    0.07
    存货
    0.06
     sr
    0.06
     Boehner
    0.06
     sàn
    0.06
    	doc
    0.06
    plt
    0.06
    Act Density 0.207%

    No Known Activations