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

    Neuronpedia

    INDEX
    Explanations

    busy doing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.88
    ’
    0.83
    تان
    0.70
     سمجھ
    0.69
     паспорт
    0.63
     warfarin
    0.63
    ları
    0.62
     stimul
    0.61
    อย่างไร
    0.61
     pak
    0.61
    POSITIVE LOGITS
    im
    1.01
    u
    1.01
    ik
    0.94
     Gelegenheit
    0.93
    ic
    0.91
    ad
    0.91
    ة
    0.86
    ir
    0.85
    á
    0.83
    ü
    0.81
    Act Density 0.002%

    No Known Activations