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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    वाईसी
    0.64
    రాలు
    0.63
    橑
    0.63
     തന്നെയാണ്
    0.60
    ateurs
    0.59
     dex
    0.59
     commitment
    0.59
    わる
    0.59
     축
    0.58
    φυ
    0.58
    POSITIVE LOGITS
     तुम्
    0.73
     tả
    0.69
    getitem
    0.68
    arum
    0.66
    lib
    0.65
    මු
    0.65
    figured
    0.64
     രജി
    0.63
     Sall
    0.63
     निर्धारित
    0.61
    Act Density 0.046%

    No Known Activations