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

    Neuronpedia

    INDEX
    Explanations

    upstream

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     locu
    2.02
     humano
    1.96
     !}{
    1.94
    श्रेष्ठ
    1.89
     vig
    1.88
    ))+\
    1.84
    ्तीय
    1.76
     calendario
    1.75
    ută
    1.74
     accessori
    1.74
    POSITIVE LOGITS
     Nerve
    1.87
    blogspot
    1.56
    ined
    1.51
    댁
    1.50
    ع
    1.47
     Fang
    1.46
    isierung
    1.45
    Democrats
    1.43
     الدراسي
    1.42
    ي
    1.42
    Act Density 0.003%

    No Known Activations