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

    Neuronpedia

    INDEX
    Explanations

    nature vs. nurture, desert, everyday

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    यण
    0.39
     sets
    0.38
     loyal
    0.38
     सर्व
    0.38
     Stewart
    0.38
     perhaps
    0.37
    ವ
    0.37
     lone
    0.37
     Step
    0.37
     trusted
    0.37
    POSITIVE LOGITS
    ூட்
    0.45
     Архив
    0.45
     تأس
    0.41
     உயரம்
    0.40
    的公司
    0.40
    ('@
    0.39
    腻
    0.39
     වශ
    0.39
     انسٹ
    0.39
    uenti
    0.38
    Act Density 0.000%

    No Known Activations