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

    Neuronpedia

    INDEX
    Explanations

    normal and uniform distributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    entennial
    -0.76
     virtualization
    -0.76
     gracilis
    -0.75
    amanan
    -0.74
    милия
    -0.73
    श्चित
    -0.73
     canadensis
    -0.72
     aerolí
    -0.72
     kwiaty
    -0.71
    OrderDetail
    -0.70
    POSITIVE LOGITS
     uniform
    2.17
     Uniform
    2.13
    Uniform
    2.03
    uniform
    2.03
     Normal
    1.85
     Gaussian
    1.80
    Normal
    1.72
     uniformly
    1.70
     normal
    1.69
    normal
    1.48
    Act Density 0.064%

    No Known Activations