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

    Neuronpedia

    INDEX
    Explanations

    6

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     material
    0.81
     Cong
    0.68
    alie
    0.68
    material
    0.66
     approval
    0.66
     달려
    0.65
     மூன்று
    0.64
     bild
    0.63
    пати
    0.62
     کیا
    0.62
    POSITIVE LOGITS
    MovieList
    0.69
    ದ್ಧ
    0.68
     habrá
    0.66
     خواهند
    0.65
    getProgress
    0.65
    setVertical
    0.63
     unprotected
    0.63
    err
    0.62
    خواهد
    0.62
    putExtra
    0.61
    Act Density 0.003%

    No Known Activations