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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    참
    -0.07
     arac
    -0.06
     ].
    -0.06
     Peygamber
    -0.06
    يري
    -0.06
    _ud
    -0.06
     hurdles
    -0.06
    HELP
    -0.06
    /issues
    -0.06
    ंदर
    -0.06
    POSITIVE LOGITS
    Typography
    0.07
    MH
    0.07
    648
    0.06
    CELL
    0.06
    이버
    0.06
     setOpen
    0.06
    (enable
    0.06
    _dyn
    0.06
    (speed
    0.06
     сбор
    0.06
    Act Density 0.001%

    No Known Activations