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

    Neuronpedia

    INDEX
    Explanations

    network speeds, ratings, chords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     μετά
    0.71
     notori
    0.68
     meriye
    0.65
     dyst
    0.61
     minutos
    0.61
     vibhav
    0.61
     considérons
    0.61
     trudno
    0.60
    ক্ষিতে
    0.60
     problemi
    0.59
    POSITIVE LOGITS
    ↵
    0.91
    <0x0D>
    0.73
    s
    0.71
    ल
    0.71
    (
    0.70
    ی
    0.65
    in
    0.62
    ي
    0.62
    +
    0.60
    ة
    0.60
    Act Density 0.022%

    No Known Activations