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

    Neuronpedia

    INDEX
    Explanations

    cuteest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    é
    0.93
    uos
    0.84
    angé
    0.82
    ㎢
    0.80
    üe
    0.79
    én
    0.77
    ća
    0.77
    Rüyada
    0.76
    োপাধ্যায়
    0.76
    it
    0.76
    POSITIVE LOGITS
     的
    0.88
    在
    0.86
    ‪
    0.86
     ſ
    0.84
     े
    0.84
    ‬
    0.84
     ‪
    0.82
    נ
    0.78
    可以
    0.77
     не
    0.76
    Act Density 0.232%

    No Known Activations