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

    Neuronpedia

    INDEX
    Explanations

    logistic regression, features, statistical analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    labyrinth
    0.79
    OpenJDK
    0.79
     entsch
    0.75
    Authent
    0.75
    لكتر
    0.75
    localStorage
    0.75
    Programm
    0.74
    Minecraft
    0.72
     Athen
    0.69
    Bitt
    0.69
    POSITIVE LOGITS
     covariates
    1.62
     regression
    1.62
     covariate
    1.58
     covariance
    1.58
     univariate
    1.56
     outliers
    1.52
     multivariate
    1.49
     quantile
    1.48
     bivariate
    1.45
     statistical
    1.44
    Act Density 1.146%

    No Known Activations