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

    Neuronpedia

    INDEX
    Explanations

    controlled accumulating manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     drap
    0.46
     Overlay
    0.38
     Termin
    0.37
    вей
    0.37
    িলো
    0.34
     catalyzes
    0.33
     stry
    0.33
     designating
    0.33
     Placing
    0.33
     Symfony
    0.33
    POSITIVE LOGITS
    他們的
    0.59
    their
    0.53
    Amounts
    0.50
    Amount
    0.48
    金額
    0.48
    萬元
    0.47
     नमू
    0.46
     AMOUNT
    0.45
     questi
    0.44
     금액
    0.44
    Act Density 0.001%

    No Known Activations