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

    Neuronpedia

    INDEX
    Explanations

    can override

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hashed
    0.51
     autopsy
    0.50
    تحان
    0.49
     यह
    0.48
    هم
    0.48
    avoid
    0.48
    اه
    0.48
     thoracique
    0.47
     carnage
    0.47
    backdrop
    0.47
    POSITIVE LOGITS
     plainly
    0.44
     prominent
    0.43
    权
    0.42
     proliferating
    0.41
    enciais
    0.40
    ęt
    0.40
     ジャン
    0.39
     രാഷ്ട്രീയ
    0.39
    雅
    0.39
     ligne
    0.38
    Act Density 0.002%

    No Known Activations