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

    Neuronpedia

    INDEX
    Explanations

    primary focus or category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    办法
    3.00
    ২০
    2.92
     применя
    2.69
    Chúng
    2.67
     லட்சம்
    2.66
    lf
    2.60
     целью
    2.58
     మంది
    2.57
    б
    2.57
    argeon
    2.54
    POSITIVE LOGITS
    ب
    3.52
    k
    3.30
    م
    3.12
    𝘴
    3.10
    ました
    3.08
    ি
    3.08
    𝗍
    3.05
     zwar
    3.02
    ർ
    2.97
    지에
    2.93
    Act Density 0.066%

    No Known Activations