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

    Neuronpedia

    INDEX
    Explanations

    special characters and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ones
    0.50
    ely
    0.49
    ans
    0.48
    on
    0.46
    ib
    0.46
    ons
    0.45
    I
    0.44
    antes
    0.44
     (=
    0.43
    apan
    0.42
    POSITIVE LOGITS
    getCharAt
    0.42
    لین
    0.41
     sassy
    0.41
     Pé
    0.40
     হন্ড
    0.40
    യാൾ
    0.40
     sante
    0.40
     sağlı
    0.39
    鵃
    0.39
     吴
    0.39
    Act Density 0.002%

    No Known Activations