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

    Neuronpedia

    INDEX
    Explanations

    builds upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    რ
    1.00
     смы
    0.89
    뜯
    0.88
     исключительно
    0.86
     svr
    0.86
    ଙ
    0.85
     attham
    0.84
    ᑉ
    0.84
    ాల
    0.82
    ARCHIVO
    0.82
    POSITIVE LOGITS
    くちゃ
    0.87
     giornal
    0.79
     dendritic
    0.78
    ↵
    0.73
     acqua
    0.73
     characterizes
    0.71
    für
    0.71
    ذية
    0.70
     dist
    0.69
    चर
    0.69
    Act Density 0.001%

    No Known Activations