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
    .ctx
    -0.08
     belli
    -0.07
    ']].
    -0.06
    را
    -0.06
     srdce
    -0.06
     кни
    -0.06
     humility
    -0.06
     Bravo
    -0.06
    рою
    -0.06
    WindowText
    -0.06
    POSITIVE LOGITS
    Overall
    0.07
    (arr
    0.06
     Officer
    0.06
    _BO
    0.06
     Highest
    0.06
     confirming
    0.06
     knowing
    0.06
     Makes
    0.06
     Pl
    0.06
    	Assert
    0.06
    Act Density 0.007%

    No Known Activations