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

    Neuronpedia

    INDEX
    Explanations

    c# programming language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.99
     письма
    0.96
     ی
    0.93
    {
    0.91
     ۹
    0.89
    జేపీ
    0.89
    ಷ್ಣ
    0.89
    Ꮷ
    0.88
     you
    0.88
     syphilis
    0.86
    POSITIVE LOGITS
    ע
    1.54
    ن
    1.43
    al
    1.40
    ul
    1.36
    ور
    1.34
    ol
    1.32
    ુ
    1.22
    ן
    1.20
    ل
    1.19
    ם
    1.17
    Act Density 0.009%

    No Known Activations