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

    Neuronpedia

    INDEX
    Explanations

    products and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    histogram
    0.63
    trivial
    0.60
     MNIST
    0.57
     covariates
    0.57
     Solidity
    0.56
    ལ་
    0.55
    rivial
    0.55
    oplas
    0.55
    jboss
    0.54
     perverse
    0.54
    POSITIVE LOGITS
     Series
    1.35
     series
    1.35
     serie
    1.17
     models
    1.14
     modèle
    1.13
    シリーズ
    1.12
     modèles
    1.12
    series
    1.12
    Series
    1.12
    系列
    1.11
    Act Density 0.450%

    No Known Activations