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

    Neuronpedia

    INDEX
    Explanations

    technical explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Males
    0.73
     stanov
    0.68
    ‌
    0.67
    ቪ
    0.63
     иностранных
    0.63
     mensuales
    0.63
     Ihre
    0.62
     Ihren
    0.62
     minuten
    0.62
     emociones
    0.61
    POSITIVE LOGITS
    čit
    0.88
    0.80
     ಯಾ
    0.79
     Incidentally
    0.78
    plicit
    0.78
    后面的
    0.78
    燬
    0.78
     $-\
    0.78
    ।--
    0.78
     bunun
    0.76
    Act Density 0.084%

    No Known Activations