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

    Neuronpedia

    INDEX
    Explanations

    FastAPI examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    0.82
     monto
    0.73
    ➢
    0.72
     supersede
    0.72
    Colour
    0.71
    ので
    0.71
    Provenance
    0.71
    もちろん
    0.69
    Concern
    0.69
     गेंदों
    0.69
    POSITIVE LOGITS
    ería
    0.73
    ান্ত্রিক
    0.73
    ňuje
    0.70
    ά
    0.70
    𝚞
    0.70
    arono
    0.68
    𝚢
    0.66
     Органи
    0.66
    erful
    0.65
    ע
    0.65
    Act Density 0.001%

    No Known Activations