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

    Neuronpedia

    INDEX
    Explanations

    math and mathematics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.82
     μεγάλη
    0.79
    ್ಯೂ
    0.77
    hj
    0.76
    I
    0.76
    ﺲ
    0.72
    hält
    0.72
    hrm
    0.72
    ﺖ
    0.71
    hle
    0.70
    POSITIVE LOGITS
    '
    0.96
     math
    0.92
    ก
    0.89
    าก
    0.87
    ุ
    0.84
    }$
    0.79
     Mathematics
    0.79
     matematik
    0.78
     matemat
    0.76
     математи
    0.75
    Act Density 0.437%

    No Known Activations