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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (withId
    -0.07
    "display
    -0.06
    mon
    -0.06
     isAuthenticated
    -0.06
    िकल
    -0.06
    _find
    -0.06
     دهید
    -0.06
    emes
    -0.06
     Tests
    -0.06
     artist
    -0.06
    POSITIVE LOGITS
     Ludwig
    0.07
     forfe
    0.06
     وجود
    0.06
    ":"",↵
    0.06
    _lost
    0.06
    朋
    0.06
    呆
    0.06
     Прав
    0.06
     sucked
    0.06
    Wie
    0.06
    Act Density 0.004%

    No Known Activations