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

    Neuronpedia

    INDEX
    Explanations

    teaching you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    miştir
    0.63
    ož
    0.63
     Tage
    0.61
     sayı
    0.60
    습니다
    0.59
    Ouest
    0.59
    Repost
    0.59
    য়াছে
    0.59
    adaşlar
    0.59
    ujjati
    0.59
    POSITIVE LOGITS
    ס
    0.87
     совета
    0.61
    ⚕
    0.61
    क्टूबर
    0.60
     dưỡng
    0.60
     gosh
    0.59
    ite
    0.59
     colleges
    0.58
     brady
    0.57
     শিক্ষিত
    0.56
    Act Density 4.906%

    No Known Activations