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

    Neuronpedia

    INDEX
    Explanations

    table showing or summarizing data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     цепо
    0.53
     одну
    0.49
     desks
    0.48
     దాని
    0.47
     сделать
    0.46
     деся
    0.44
     mockup
    0.44
     девя
    0.43
     नक्
    0.43
     निर्धारित
    0.43
    POSITIVE LOGITS
    Argent
    0.44
     عوامل
    0.41
    Beta
    0.39
     Afgan
    0.39
     Beta
    0.38
    性は
    0.38
    Brown
    0.38
    Table
    0.38
    Bet
    0.37
    刃
    0.37
    Act Density 0.070%

    No Known Activations