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

    Neuronpedia

    INDEX
    Explanations

    what questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ктак
    0.41
    改编
    0.41
     його
    0.40
     শিক্ষক
    0.40
    ᓵ
    0.40
    溘
    0.39
     учи
    0.39
    敺
    0.38
     તેના
    0.38
     খেলার
    0.37
    POSITIVE LOGITS
    0
    0.55
    light
    0.52
    la
    0.51
    ni
    0.48
    south
    0.48
    n
    0.48
     runny
    0.47
    lets
    0.47
    wat
    0.46
    sp
    0.46
    Act Density 0.002%

    No Known Activations