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

    Neuronpedia

    INDEX
    Explanations

    languages and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    é
    1.77
    --
    1.51
    نا
    1.48
    —
    1.45
    ur
    1.43
    è
    1.32
    ,
    1.32
    /
    1.31
    s
    1.30
    ---
    1.19
    POSITIVE LOGITS
    এর
    1.88
     Dette
    1.84
     Đó
    1.80
    ので
    1.78
     Özellikle
    1.78
     тобто
    1.75
     Tiếp
    1.72
     Untuk
    1.68
     Hence
    1.63
     第
    1.63
    Act Density 0.393%

    No Known Activations