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

    Neuronpedia

    INDEX
    Explanations

    structured lists and notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ሔ
    0.39
     معاش
    0.38
    嗣
    0.37
     tí
    0.36
    Jeh
    0.36
    ণ্ডল
    0.36
    ρευ
    0.36
     ophthal
    0.36
     entreprene
    0.35
     estím
    0.35
    POSITIVE LOGITS
     बलराम
    0.42
     अपलोड
    0.42
     Pokud
    0.41
    ಇ
    0.40
     यूज
    0.40
    丢
    0.39
    ebug
    0.39
     உள்ளது
    0.38
     போட்டிய
    0.38
    ﾌ
    0.38
    Act Density 0.078%

    No Known Activations