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

    Neuronpedia

    INDEX
    Explanations

    physical, divine, visual, legend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Esp
    0.43
    Esp
    0.43
    Marsh
    0.42
    ologo
    0.38
    varnothing
    0.37
    unting
    0.37
    esign
    0.37
    Ø
    0.37
    iling
    0.36
    esp
    0.36
    POSITIVE LOGITS
    哏
    0.45
     እንዴት
    0.44
    𒌅
    0.43
    然后
    0.41
     കലാ
    0.41
    டக்கலை
    0.40
    ಕು
    0.40
    蓝
    0.40
    ována
    0.39
     红
    0.39
    Act Density 0.000%

    No Known Activations