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

    Neuronpedia

    INDEX
    Explanations

    high levels and changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iklet
    0.46
    濂
    0.46
    采用了
    0.45
    لي
    0.44
    bergh
    0.43
    σσ
    0.43
    idina
    0.43
    鹦
    0.42
    били
    0.41
    änä
    0.41
    POSITIVE LOGITS
    ജെ
    0.57
     brokerage
    0.51
     ethnicity
    0.50
     בה
    0.50
     fraîche
    0.50
     impuls
    0.50
     tez
    0.49
     نظری
    0.49
     brok
    0.48
     ต้น
    0.47
    Act Density 0.000%

    No Known Activations