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

    Neuronpedia

    INDEX
    Explanations

    offensive content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pomocí
    0.47
     используя
    0.44
    تھی
    0.42
    λέ
    0.40
     utilizzare
    0.40
     작성
    0.40
    可以用
    0.40
     لکھنے
    0.39
    rewrite
    0.38
    除非
    0.38
    POSITIVE LOGITS
     provisional
    0.46
     fique
    0.44
     minor
    0.44
     subsequently
    0.44
     undetected
    0.44
     remain
    0.44
     ahead
    0.44
     Müdür
    0.42
     Remaining
    0.42
     subsequent
    0.42
    Act Density 0.003%

    No Known Activations