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

    Neuronpedia

    INDEX
    Explanations

    multilingual text inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     up
    0.71
    गर
    0.68
    ANDE
    0.68
     வரை
    0.67
    맬
    0.67
     Instit
    0.67
    RIBUTES
    0.66
    ادث
    0.66
    ரிக்கை
    0.65
    字段
    0.65
    POSITIVE LOGITS
     deci
    0.78
     donnant
    0.74
    اشت
    0.68
     hol
    0.67
     হ
    0.66
     apunt
    0.63
     కళ
    0.63
     ਚ
    0.63
     ቀ
    0.62
     too
    0.62
    Act Density 0.000%

    No Known Activations