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

    Neuronpedia

    INDEX
    Explanations

    Caroline, Alexandra, Nadine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    2.27
    ol
    2.05
    أس
    2.02
    é
    1.96
    ש
    1.96
    أ
    1.90
    Е
    1.89
    Д
    1.87
    Β
    1.87
    ing
    1.85
    POSITIVE LOGITS
     Estud
    1.95
    нием
    1.77
    yya
    1.75
     calific
    1.71
     plaques
    1.69
    ્સ
    1.66
     wardrobes
    1.65
     bangle
    1.60
     nostrils
    1.59
    overnment
    1.57
    Act Density 0.000%

    No Known Activations