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

    Neuronpedia

    INDEX
    Explanations

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     이러한
    0.70
     ascertaining
    0.63
    <unused2063>
    0.63
    នៃ
    0.62
     бухгалтер
    0.62
     ignoreString
    0.61
     banknotes
    0.60
     safeguarding
    0.59
    <unused432>
    0.59
    <unused520>
    0.59
    POSITIVE LOGITS
     باشه
    0.84
    してる
    0.79
    ってる
    0.75
     đc
    0.73
     wasnt
    0.70
    us
    0.67
    T
    0.67
    at
    0.66
     vs
    0.66
    es
    0.65
    Act Density 0.002%

    No Known Activations