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

    Neuronpedia

    INDEX
    Explanations

    "Let's" followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     полностью
    0.91
    不受
    0.87
     довольно
    0.86
    サーチ
    0.84
    𝓊
    0.83
     поэтому
    0.82
     descont
    0.82
    লো
    0.81
     alınd
    0.81
     раздра
    0.81
    POSITIVE LOGITS
     piani
    0.92
     globe
    0.86
     choisi
    0.84
    ad
    0.84
    ikis
    0.81
    nten
    0.79
    al
    0.77
    اين
    0.77
    ما
    0.76
     geographies
    0.76
    Act Density 0.000%

    No Known Activations