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

    Neuronpedia

    INDEX
    Explanations

    irrational and rational numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inverted
    0.43
     மகளிர்
    0.43
     બાળ
    0.42
    Austin
    0.42
    雌
    0.42
    Charter
    0.41
    MORPH
    0.41
    Optical
    0.41
    Ing
    0.40
    Pregnant
    0.40
    POSITIVE LOGITS
     irrational
    1.35
     rational
    1.01
     Irr
    0.89
     Rational
    0.84
     rationality
    0.82
     rationally
    0.82
     racional
    0.80
     рациона
    0.80
    rational
    0.77
     rationalize
    0.77
    Act Density 0.026%

    No Known Activations