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

    Neuronpedia

    INDEX
    Explanations

    conquering complexity or belief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    쩌
    0.67
    izedBox
    0.66
    ↵
    0.66
    ные
    0.66
     martingale
    0.66
    న్ని
    0.64
     सामने
    0.62
    gravity
    0.62
    폭
    0.61
    k
    0.61
    POSITIVE LOGITS
    𝗕
    0.89
     sentimiento
    0.84
     وهذه
    0.83
     espes
    0.82
     hizo
    0.81
     esclusivamente
    0.81
     wakt
    0.81
    お金
    0.81
     manifestó
    0.81
    कृपया
    0.80
    Act Density 0.001%

    No Known Activations