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

    Neuronpedia

    INDEX
    Explanations

    bel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Restrictions
    -0.07
    Become
    -0.07
     खबर
    -0.07
    Criteria
    -0.07
     AssertionError
    -0.06
     clientes
    -0.06
     نزدیک
    -0.06
    _strerror
    -0.06
     이상
    -0.06
    ThanOrEqualTo
    -0.06
    POSITIVE LOGITS
     się
    0.07
    ellig
    0.07
    élé
    0.07
    .AD
    0.07
    貝
    0.07
    จร
    0.07
     Dolphin
    0.06
     maxWidth
    0.06
     гем
    0.06
    BAR
    0.06
    Act Density 0.006%

    No Known Activations