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

    Neuronpedia

    INDEX
    Explanations

    API calls and model loading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fémin
    0.31
     benöt
    0.29
    できません
    0.29
     usuário
    0.28
     Beyoncé
    0.28
     chhoti
    0.28
    ivität
    0.28
     Lernen
    0.28
     kullanıcı
    0.28
     محصول
    0.27
    POSITIVE LOGITS
    Dis
    0.26
    pins
    0.26
    Б
    0.25
    Agr
    0.25
    ам
    0.24
    ΕΣ
    0.24
    Suc
    0.24
     сказала
    0.24
    pineapple
    0.24
    мур
    0.24
    Act Density 0.031%

    No Known Activations