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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    βα
    -0.06
    들
    -0.06
    _stand
    -0.06
    цит
    -0.06
     Inspection
    -0.06
     comments
    -0.06
     iteration
    -0.06
     Functor
    -0.06
     �
    -0.06
     adını
    -0.06
    POSITIVE LOGITS
     interstate
    0.07
    	contentPane
    0.07
    (Mouse
    0.07
    xBE
    0.07
     authenticate
    0.06
    ousel
    0.06
     NSAttributedString
    0.06
     کیل
    0.06
    ────
    0.06
     کامپی
    0.06
    Act Density 0.073%

    No Known Activations