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

    Neuronpedia

    INDEX
    Explanations

    misspellings followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Когда
    0.55
    Hepin
    0.54
    then
    0.54
     tasmim
    0.53
     Несмотря
    0.52
    arxiv
    0.52
    ിയും
    0.51
    OUS
    0.50
    recorder
    0.50
     Иң
    0.49
    POSITIVE LOGITS
    ,
    0.83
    -
    0.82
    َ
    0.66
    س
    0.63
     bale
    0.63
    ن
    0.61
     por
    0.58
     pastel
    0.58
    =
    0.58
     to
    0.57
    Act Density 0.000%

    No Known Activations