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

    Neuronpedia

    INDEX
    Explanations

    algebraic expressions and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    waitKey
    0.48
    ುದ
    0.39
    ChessBot
    0.39
    忄
    0.38
     ইয়াহিয়ার
    0.38
    িত্ত
    0.37
    ંદા
    0.37
    phosphorylation
    0.37
    }$-(
    0.37
    individu
    0.37
    POSITIVE LOGITS
     $-
    0.55
    ²+
    0.49
    ^
    0.47
     $+
    0.45
     +
    0.45
     -
    0.44
    ²
    0.43
    ^{
    0.43
    (-
    0.41
     quadrado
    0.40
    Act Density 0.035%

    No Known Activations