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

    Neuronpedia

    INDEX
    Explanations

    mathematical and programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    efois
    0.29
     bañ
    0.29
    犒
    0.28
     കൂടുത
    0.27
     волосы
    0.27
    स्ट्रेल
    0.26
     êtes
    0.26
    <unused2020>
    0.26
     яго
    0.26
    싶
    0.26
    POSITIVE LOGITS
     of
    0.43
     (
    0.39
    .
    0.38
     with
    0.37
    （
    0.37
    ,
    0.37
    -
    0.36
     and
    0.35
     for
    0.31
     by
    0.31
    Act Density 0.935%

    No Known Activations