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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     б
    -0.07
     Rewards
    -0.07
     раді
    -0.06
     Lift
    -0.06
    'im
    -0.06
    wend
    -0.06
     chó
    -0.06
     GPL
    -0.06
     Hal
    -0.06
     spur
    -0.06
    POSITIVE LOGITS
     @{
    0.07
    _take
    0.06
     Іван
    0.06
    _slices
    0.06
    assertFalse
    0.06
     ظرف
    0.06
    334
    0.06
    ._↵↵
    0.06
    	let
    0.06
     Gover
    0.06
    Act Density 0.000%

    No Known Activations