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

    Neuronpedia

    INDEX
    Explanations

    code structure namespaces and directories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iferous
    0.37
    icuous
    0.35
    íbrio
    0.34
     על
    0.34
    imetric
    0.34
     ड
    0.33
    isive
    0.32
    ariest
    0.32
     ventral
    0.32
     Pythagorean
    0.32
    POSITIVE LOGITS
    utils
    0.51
    enums
    0.50
    model
    0.49
    Utils
    0.46
    Constants
    0.46
    common
    0.45
    config
    0.43
    util
    0.42
    models
    0.42
    constants
    0.41
    Act Density 0.018%

    No Known Activations