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

    Neuronpedia

    INDEX
    Explanations

    equations and objects in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    1.04
    t
    0.96
    glicherweise
    0.80
    chmod
    0.78
    uoj
    0.77
    uction
    0.76
    ઁ
    0.75
    ck
    0.75
    চ্ছা
    0.75
    慟
    0.74
    POSITIVE LOGITS
     fraudulently
    0.82
     команды
    0.80
     suje
    0.77
     Qualquer
    0.77
    ATIV
    0.76
    ABAB
    0.75
    賴
    0.75
    Cumulative
    0.73
     مطلق
    0.73
     накопи
    0.72
    Act Density 0.003%

    No Known Activations