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

    Neuronpedia

    INDEX
    Explanations

    after examples or considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     جیس
    0.50
    稣
    0.49
    耶稣
    0.48
    蚓
    0.47
    Changed
    0.47
    Результа
    0.47
    Jest
    0.46
     realizzazione
    0.46
     പരിശ
    0.46
     Virgil
    0.46
    POSITIVE LOGITS
    },\
    0.44
     toekom
    0.43
     IUnary
    0.42
     امشي
    0.41
    ${
    0.40
     લાઇ
    0.39
     갔
    0.39
     διε
    0.39
     휴대
    0.39
     長
    0.39
    Act Density 0.001%

    No Known Activations