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

    Neuronpedia

    INDEX
    Explanations

    formatted lists and arrays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    হয়
    0.80
     عيد
    0.71
     resigned
    0.70
     conquist
    0.69
    鸯
    0.69
    чами
    0.68
    ključ
    0.68
    eslintrc
    0.68
    ိုလ်
    0.67
    ነት
    0.67
    POSITIVE LOGITS
     LAST
    0.78
    FORWARD
    0.76
    ↵
    0.74
    Processing
    0.73
    Cookies
    0.73
    os
    0.72
     послед
    0.72
     맞는
    0.72
    μμ
    0.71
     последних
    0.71
    Act Density 0.001%

    No Known Activations