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

    Neuronpedia

    INDEX
    Explanations

    infinities in mathematical calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻚ
    0.47
     ipotesi
    0.45
    ӥ
    0.44
    illusion
    0.43
     ہاکی
    0.43
     ಘೋಷ
    0.43
    沔
    0.42
    匽
    0.42
    立
    0.42
     மிசோ
    0.41
    POSITIVE LOGITS
     calculations
    0.69
     calculation
    0.66
     predictions
    0.64
     logarithms
    0.63
     Calculations
    0.59
     corrections
    0.59
     perturbative
    0.57
     computations
    0.56
     correction
    0.55
     calculating
    0.55
    Act Density 0.007%

    No Known Activations