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

    Neuronpedia

    INDEX
    Explanations

    investing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bruger
    0.54
     neuesten
    0.46
    ريكية
    0.44
    嫒
    0.42
     základě
    0.41
     brunette
    0.40
     वर्णन
    0.40
    ினர்
    0.40
     anzeigen
    0.40
    ชน์
    0.39
    POSITIVE LOGITS
    in
    0.45
    of
    0.41
     चुनौ
    0.38
    ᄀ
    0.38
    iou
    0.38
     время
    0.38
    ities
    0.38
    ofa
    0.37
    Options
    0.37
    ᄇ
    0.37
    Act Density 0.008%

    No Known Activations