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

    Neuronpedia

    INDEX
    Explanations

    after the parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    考核
    0.53
     infirm
    0.52
     Simons
    0.52
     HMO
    0.50
     Brahmin
    0.50
     întâ
    0.50
     morale
    0.49
     siglas
    0.49
     stagione
    0.49
     moan
    0.49
    POSITIVE LOGITS
    То
    0.59
    ש
    0.53
    ла
    0.52
    ک
    0.47
    Ul
    0.47
    them
    0.45
    Ö
    0.45
    任务
    0.44
    sensor
    0.44
    Очень
    0.43
    Act Density 0.000%

    No Known Activations