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

    Neuronpedia

    INDEX
    Explanations

    foreign languages and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    1.06
    ก
    1.03
    m
    0.92
     not
    0.88
     that
    0.87
     the
    0.86
     decentral
    0.85
    મ
    0.84
    b
    0.82
     be
    0.80
    POSITIVE LOGITS
    .
    1.31
    ت
    1.20
    ۔
    1.13
    ․
    1.04
    고
    1.03
    تمد
    0.98
    تهم
    0.95
     diuretics
    0.95
    4
    0.95
    া
    0.95
    Act Density 0.993%

    No Known Activations