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

    Neuronpedia

    INDEX
    Explanations

    matplotlib.pyplot import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ழு
    0.39
    ittu
    0.39
     સંપૂર્ણ
    0.38
    Rafael
    0.38
    ᠢ
    0.38
    ţi
    0.38
     তড়
    0.38
    anski
    0.37
     পা
    0.36
    ма
    0.36
    POSITIVE LOGITS
     piensa
    0.45
    ["
    0.38
     condom
    0.36
     dex
    0.36
     Trojans
    0.36
    都不会
    0.35
     précise
    0.35
    <<(
    0.35
     Trojan
    0.34
     involution
    0.34
    Act Density 0.001%

    No Known Activations