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

    Neuronpedia

    INDEX
    Explanations

    comparisons of large/small groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tim
    -0.08
    -analytics
    -0.07
    ugas
    -0.07
    amide
    -0.07
    Witness
    -0.07
     eco
    -0.07
    Estimated
    -0.07
    .timezone
    -0.06
     Acceler
    -0.06
     Bedford
    -0.06
    POSITIVE LOGITS
    ології
    0.06
    лся
    0.06
    вержд
    0.06
    _categoria
    0.06
    (storage
    0.06
    \"",
    0.06
     эф
    0.06
     &_
    0.06
    cheng
    0.06
    >H
    0.06
    Act Density 0.030%

    No Known Activations