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

    Neuronpedia

    INDEX
    Explanations

    Fight the New Drug

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     países
    0.42
     há
    0.38
     phú
    0.37
     Jürgen
    0.36
     país
    0.36
     racist
    0.36
     ഉണ്ടാ
    0.36
     massimo
    0.36
     fascist
    0.36
     yoki
    0.35
    POSITIVE LOGITS
    蛲
    0.38
    Му
    0.38
    图书馆
    0.38
     библиоте
    0.36
    Sexual
    0.36
    圣
    0.35
    怀孕
    0.35
    MD
    0.34
    此
    0.33
    На
    0.33
    Act Density 0.043%

    No Known Activations