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

    Neuronpedia

    INDEX
    Explanations

    modular arithmetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    文本
    0.44
     azimuth
    0.44
    蜥
    0.39
     brahm
    0.39
     enanti
    0.39
    ضو
    0.38
    ครื่อง
    0.38
    Euler
    0.38
     sudoku
    0.37
     Euler
    0.36
    POSITIVE LOGITS
     обви
    0.41
    신
    0.39
    꼼
    0.39
     регу
    0.38
     paraf
    0.38
    ობა
    0.37
     DIA
    0.37
     sob
    0.36
     называ
    0.36
    ')));
    0.36
    Act Density 0.000%

    No Known Activations