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

    Neuronpedia

    INDEX
    Explanations

    invocation nor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    其他
    0.51
    ↵↵
    0.50
    type
    0.48
    '
    0.46
    kv
    0.46
    print
    0.46
    st
    0.46
    cit
    0.45
    ts
    0.45
    time
    0.45
    POSITIVE LOGITS
     忄
    0.59
    ጶ
    0.51
     scrollBody
    0.50
     обработки
    0.49
    ާއި
    0.49
     هەر
    0.48
    🐯
    0.48
    ложении
    0.48
    ява
    0.48
    явления
    0.48
    Act Density 0.000%

    No Known Activations