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

    Neuronpedia

    INDEX
    Explanations

    formatting and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ar
    0.78
    ल
    0.77
    ص
    0.74
    কে
    0.71
    баров
    0.70
    лити
    0.69
     কিছুর
    0.68
    ли
    0.68
    ക്കോ
    0.68
    ro
    0.66
    POSITIVE LOGITS
     nga
    0.97
    Якщо
    0.91
    Жен
    0.90
    iyor
    0.89
     vutta
    0.89
     bhave
    0.89
     vutt
    0.88
    س
    0.88
    ᓃ
    0.87
     costituito
    0.87
    Act Density 0.000%

    No Known Activations