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

    Neuronpedia

    INDEX
    Explanations

    vector direction calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ії
    0.73
    पृथ
    0.71
    ֔
    0.71
    كية
    0.70
    ନ୍ତି
    0.69
     überhaupt
    0.68
     Pemerintah
    0.68
     morphisms
    0.68
    詄
    0.68
    AOrdenar
    0.67
    POSITIVE LOGITS
    url
    0.69
     calculate
    0.68
    F
    0.68
    README
    0.68
    进度
    0.67
    その
    0.66
    ']=
    0.66
     이때
    0.66
    V
    0.65
     ভাইকে
    0.64
    Act Density 0.000%

    No Known Activations