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

    Neuronpedia

    INDEX
    Explanations

    laws governing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HLIGHT
    1.86
    ES
    1.85
    MIS
    1.80
     поводу
    1.77
    OFF
    1.71
    LOT
    1.70
     Chicks
    1.70
    genes
    1.67
    MAS
    1.67
    িয়েছে
    1.67
    POSITIVE LOGITS
    ни
    2.73
    ור
    2.22
    ные
    2.14
    но
    2.09
    ко
    2.03
    ور
    2.00
    ू
    1.98
    에
    1.98
    ী
    1.87
    ్‌
    1.85
    Act Density 0.018%

    No Known Activations