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

    Neuronpedia

    INDEX
    Explanations

    language identification and translation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cot
    0.54
    Pen
    0.49
    Bur
    0.48
    Kot
    0.48
    Ő
    0.46
    Game
    0.46
    ্রি
    0.46
    Protein
    0.44
    Uk
    0.44
    。
    0.43
    POSITIVE LOGITS
    ופ
    0.57
    티브
    0.56
    omes
    0.50
    வய
    0.50
    படுத்த
    0.49
     tuvieron
    0.49
     तैनात
    0.48
     של
    0.48
     disponibles
    0.48
    adigan
    0.48
    Act Density 0.000%

    No Known Activations