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

    Neuronpedia

    INDEX
    Explanations

    seven

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fonte
    0.46
    Princeton
    0.42
    HMS
    0.41
     footnotes
    0.40
    狨
    0.40
     usern
    0.39
     puntual
    0.38
     fonte
    0.38
     Atlet
    0.37
     Hunde
    0.37
    POSITIVE LOGITS
     seventh
    0.73
     tujuh
    0.69
     seven
    0.68
     ஏழு
    0.68
     七
    0.68
    七
    0.65
     Seven
    0.64
     सात
    0.64
     هفت
    0.63
    seven
    0.63
    Act Density 0.075%

    No Known Activations