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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outward
    -0.07
     புர
    -0.07
     excursion
    -0.07
    tent
    -0.07
    ucos
    -0.07
     বো
    -0.07
     shak
    -0.07
     immensely
    -0.07
     Bub
    -0.07
     সুন্দর
    -0.07
    POSITIVE LOGITS
    达
    0.09
     حصول
    0.08
    达到
    0.08
     الحصول
    0.08
     achieve
    0.08
     طول
    0.08
     atingir
    0.08
     رسید
    0.08
     ل
    0.08
     تحقيق
    0.08
    Act Density 0.013%

    No Known Activations