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

    Neuronpedia

    INDEX
    Explanations

    but not a direct question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    emptyDict
    0.50
    }{|\
    0.48
     שא
    0.48
    pInBuffer
    0.47
     படங்கள்
    0.45
     sayılı
    0.43
    訸
    0.43
     సెల
    0.42
     नाक
    0.42
    蝿
    0.42
    POSITIVE LOGITS
     de
    0.58
     as
    0.54
     to
    0.50
     of
    0.50
     before
    0.46
     even
    0.45
     albeit
    0.45
     but
    0.45
     noticias
    0.44
     ennen
    0.43
    Act Density 0.007%

    No Known Activations