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

    Neuronpedia

    INDEX
    Explanations

    but situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     équipe
    0.47
    ئین
    0.47
     پیغم
    0.46
     رکھتی
    0.45
    顰
    0.45
    闖
    0.44
     انجن
    0.44
    inney
    0.43
    otherapist
    0.42
    amir
    0.42
    POSITIVE LOGITS
     }{
    0.47
    '},
    0.43
    }$
    0.43
     }
    0.41
    িসি
    0.41
    }^{-
    0.40
     الته
    0.40
     toler
    0.40
    צוני
    0.39
    مكان
    0.39
    Act Density 0.003%

    No Known Activations