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

    Neuronpedia

    INDEX
    Explanations

    population changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     крови
    -0.07
    :D
    -0.06
    Unit
    -0.06
    "But
    -0.06
    *R
    -0.06
    VERSE
    -0.06
    —but
    -0.06
    posit
    -0.06
    But
    -0.06
    xoops
    -0.06
    POSITIVE LOGITS
     represent
    0.07
     SMALL
    0.07
    860
    0.07
    _yellow
    0.07
    .system
    0.07
    λι
    0.06
     Phillies
    0.06
    слов
    0.06
    ／／
    0.06
    dej
    0.06
    Act Density 0.003%

    No Known Activations