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

    Neuronpedia

    INDEX
    Explanations

    code and web requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TYPEDEF
    -0.07
    _MAP
    -0.06
    -B
    -0.06
    .Batch
    -0.06
    .histogram
    -0.06
    pers
    -0.06
    UDIO
    -0.06
    лях
    -0.06
     autobiography
    -0.06
    _combined
    -0.06
    POSITIVE LOGITS
    ilities
    0.07
     Brazilian
    0.07
    говор
    0.06
    (optimizer
    0.06
     evolves
    0.06
     культури
    0.06
     espec
    0.06
     فکر
    0.06
     violently
    0.06
    ね
    0.06
    Act Density 0.034%

    No Known Activations