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

    Neuronpedia

    INDEX
    Explanations

    asked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OO
    -0.07
    �
    -0.06
    AP
    -0.06
    、い
    -0.06
     reap
    -0.06
    _period
    -0.06
     chỉnh
    -0.06
    ‌ای
    -0.06
    ヘ
    -0.06
    าศาสตร
    -0.06
    POSITIVE LOGITS
     trusted
    0.07
     honestly
    0.07
    ↵↵↵↵
    0.07
     truncated
    0.07
     sweeps
    0.07
     eng
    0.07
     林
    0.07
     Regards
    0.06
    思
    0.06
     Кор
    0.06
    Act Density 0.012%

    No Known Activations