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

    Neuronpedia

    INDEX
    Explanations

    html meta tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ள்
    1.77
     forbindelse
    1.67
     seguinte
    1.66
     contaba
    1.58
    1.56
    ు
    1.54
    ค์
    1.53
    зі
    1.52
    個月
    1.51
     zespołu
    1.51
    POSITIVE LOGITS
    1.62
    再加上
    1.57
     nd
    1.45
    外交
    1.41
     std
    1.39
    trying
    1.36
    dtype
    1.35
    een
    1.35
     posture
    1.34
    ी
    1.34
    Act Density 0.003%

    No Known Activations