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

    Neuronpedia

    INDEX
    Explanations

    updating and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rational
    0.50
     rationally
    0.46
     Rational
    0.45
     transf
    0.45
    rational
    0.45
     irrational
    0.44
     starters
    0.43
     racional
    0.43
    anil
    0.42
     rationalize
    0.41
    POSITIVE LOGITS
     Died
    0.42
    Updated
    0.40
    çuk
    0.40
    ঘাত
    0.40
    的地
    0.39
    öder
    0.39
    Updating
    0.38
     умер
    0.38
    stes
    0.38
    ক্র
    0.37
    Act Density 0.001%

    No Known Activations