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

    Neuronpedia

    INDEX
    Explanations

    something never seen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дку
    0.71
    ঁ
    0.69
    ᚕ
    0.63
     unsurprisingly
    0.62
    ಟ್‌
    0.60
    ے
    0.59
    ͜
    0.59
    टी
    0.58
     Komis
    0.58
    дят
    0.57
    POSITIVE LOGITS
    et
    0.87
    ق
    0.87
    ل
    0.85
     in
    0.79
    شهر
    0.79
    ש
    0.78
    v
    0.76
     be
    0.75
    j
    0.73
    ن
    0.71
    Act Density 0.008%

    No Known Activations