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

    Neuronpedia

    INDEX
    Explanations

    to verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وت
    0.70
    OF
    0.68
    AZIONE
    0.64
    AZ
    0.63
    গোষ্ঠ
    0.63
    d
    0.63
    a
    0.62
    C
    0.62
     فريبي
    0.61
     dupa
    0.61
    POSITIVE LOGITS
    .
    0.70
     be
    0.67
    ’
    0.61
    ى
    0.60
    ize
    0.58
    ized
    0.58
    li
    0.57
    ly
    0.56
     굉장히
    0.55
    та
    0.55
    Act Density 0.016%

    No Known Activations