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

    Neuronpedia

    INDEX
    Explanations

    dialectical materialism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     separar
    0.45
     distribuição
    0.43
     sépar
    0.40
     mixto
    0.40
     touche
    0.39
     hyperlocal
    0.39
     máximo
    0.38
     autorización
    0.38
     distribution
    0.38
    发行
    0.38
    POSITIVE LOGITS
     dialect
    1.13
     Heg
    1.06
     Hegel
    1.05
    dialect
    0.96
    Dial
    0.85
     Dial
    0.84
    辩
    0.81
    辯
    0.74
     dial
    0.71
     contradictions
    0.69
    Act Density 0.010%

    No Known Activations