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

    Neuronpedia

    INDEX
    Explanations

    billions of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nuxtjs
    0.55
    choline
    0.55
    ul
    0.54
    ಲಯ
    0.53
    unprocessable
    0.52
    ਧੀ
    0.52
     மிசோரம்
    0.52
    ي
    0.52
    addColor
    0.51
    giving
    0.50
    POSITIVE LOGITS
    枺
    0.58
     సే
    0.56
    特性
    0.55
     वर्ल्ड
    0.54
     tần
    0.54
    呥
    0.52
     Atual
    0.52
     Passenger
    0.51
     motivos
    0.50
     ऊर्जा
    0.50
    Act Density 0.008%

    No Known Activations