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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas with symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     piecewise
    0.42
     implying
    0.40
     adding
    0.36
     dimensionless
    0.35
     stepwise
    0.35
     braced
    0.35
     thus
    0.34
     spurious
    0.34
     превра
    0.33
     summand
    0.33
    POSITIVE LOGITS
    es
    0.52
    aal
    0.44
    o
    0.43
    Language
    0.42
    al
    0.41
    ailles
    0.41
    chi
    0.40
    ad
    0.40
    e
    0.40
    ece
    0.40
    Act Density 0.024%

    No Known Activations