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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mostly
    -0.07
     unlaw
    -0.07
     eighty
    -0.07
     değerlendir
    -0.07
     коміс
    -0.06
     اخلاق
    -0.06
     북
    -0.06
    iação
    -0.06
    _DOWNLOAD
    -0.06
    issing
    -0.06
    POSITIVE LOGITS
    	JButton
    0.07
    structor
    0.06
    象
    0.06
    oleč
    0.06
    nels
    0.06
    _router
    0.06
    мотря
    0.06
     création
    0.06
     :\
    0.06
    ――――
    0.06
    Act Density 0.000%

    No Known Activations