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

    Neuronpedia

    INDEX
    Explanations

    context or position

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vir
    0.64
    धिकारी
    0.61
     içerisinde
    0.59
    steiner
    0.59
    ضي
    0.58
    =>
    0.57
    ና
    0.57
    اض
    0.55
    rctx
    0.55
    動
    0.55
    POSITIVE LOGITS
     ран
    0.66
     embl
    0.58
    arrant
    0.58
     лен
    0.57
     непосредственно
    0.57
    سى
    0.56
     رف
    0.56
     إل
    0.56
     tant
    0.55
     будущее
    0.55
    Act Density 0.000%

    No Known Activations