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

    Neuronpedia

    INDEX
    Explanations

    some resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Д
    0.72
     ambiguity
    0.66
     خبر
    0.64
    ⺆
    0.64
    ాన్ని
    0.62
     finiteness
    0.61
     そこ
    0.61
     Struktur
    0.61
     lati
    0.61
    provoking
    0.61
    POSITIVE LOGITS
    te
    0.75
    teilt
    0.65
    可以是
    0.65
    可以说
    0.64
     '\''
    0.63
    re
    0.62
    >>)
    0.62
    llä
    0.61
    ángulo
    0.61
     dreaded
    0.61
    Act Density 0.039%

    No Known Activations