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

    Neuronpedia

    INDEX
    Explanations

    three

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    四十
    0.50
     Forty
    0.47
    Forty
    0.44
    Twenty
    0.43
     Sixteen
    0.42
     keduanya
    0.41
     пя
    0.39
     Eighty
    0.39
    二十
    0.38
    五十
    0.38
    POSITIVE LOGITS
     three
    3.50
     Three
    3.38
    Three
    3.36
    three
    3.28
     trois
    3.20
    三
    3.11
     três
    3.09
     üç
    3.09
     THREE
    3.08
    THREE
    3.05
    Act Density 0.514%

    No Known Activations