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

    Neuronpedia

    INDEX
    Explanations

    new products and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whatnot
    0.38
    Cannot
    0.37
    <0x0D>
    0.34
    ā
    0.34
    Symbol
    0.33
    Anth
    0.33
    鸫
    0.33
    ♪
    0.33
     kerosene
    0.32
    0.32
    POSITIVE LOGITS
     ं
    0.51
     இந்த
    0.50
    valuer
    0.48
    劵
    0.47
    vollen
    0.47
    vrez
    0.46
    س
    0.46
    事を
    0.45
    nieuw
    0.44
    selves
    0.44
    Act Density 0.042%

    No Known Activations