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

    Neuronpedia

    INDEX
    Explanations

    listing alternatives in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ഹ്ലാദ
    0.36
    ğmen
    0.33
    ío
    0.33
    唝
    0.32
     ഇമാ
    0.32
    iterranée
    0.32
    öö
    0.31
    棣
    0.30
    志森
    0.30
    踞
    0.30
    POSITIVE LOGITS
    或其他
    0.74
     или
    0.68
     veya
    0.66
     or
    0.66
     hoặc
    0.62
     alebo
    0.60
    或
    0.59
     ಅಥವಾ
    0.59
     किंवा
    0.57
     أو
    0.56
    Act Density 0.554%

    No Known Activations