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

    Neuronpedia

    INDEX
    Explanations

    pronunciations and Pinyin syllables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を活用
    0.77
     بقدر
    0.69
    を使用して
    0.66
     얼마나
    0.64
     Sicherheits
    0.64
     fractions
    0.63
    が存在
    0.63
    ومت
    0.60
     triggering
    0.60
    ตน
    0.59
    POSITIVE LOGITS
    uh
    0.87
     uh
    0.78
     rh
    0.78
     plural
    0.78
    CH
    0.75
     ee
    0.75
     rescu
    0.75
    hn
    0.75
    h
    0.74
    li
    0.73
    Act Density 0.194%

    No Known Activations