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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mine
    0.75
     নিরাপদ
    0.69
     माझ्या
    0.68
     எனக்கு
    0.67
     doskona
    0.67
     নিখ
    0.66
     rare
    0.64
     Where
    0.64
    哪里
    0.64
     damos
    0.63
    POSITIVE LOGITS
     copyspace
    0.68
    izoen
    0.67
    identité
    0.66
    觟
    0.65
     Genealogical
    0.63
    チップ
    0.63
    迌
    0.62
     принято
    0.62
    отно
    0.61
    isterschaften
    0.61
    Act Density 0.014%

    No Known Activations