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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    956
    -0.07
    estyle
    -0.06
    overn
    -0.06
     Hector
    -0.06
    (push
    -0.06
    NT
    -0.06
    quee
    -0.06
    <count
    -0.06
    انگ
    -0.06
    _WARN
    -0.06
    POSITIVE LOGITS
    最大
    0.08
    highest
    0.07
     соп
    0.07
    只能
    0.06
    (gray
    0.06
    #${
    0.06
     only
    0.06
     jihadists
    0.06
    :^(
    0.06
     geopolitical
    0.06
    Act Density 0.013%

    No Known Activations