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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smoker
    -0.07
     znaj
    -0.06
    .ToolTip
    -0.06
    �ng
    -0.06
    	contentPane
    -0.06
     outrageous
    -0.06
    engin
    -0.06
     grantResults
    -0.06
    MethodManager
    -0.06
    くん
    -0.06
    POSITIVE LOGITS
    policy
    0.07
     representation
    0.06
    ần
    0.06
    _UNDER
    0.06
    (datas
    0.06
    ragon
    0.06
    040
    0.06
     adopt
    0.06
     bgColor
    0.06
    	printf
    0.06
    Act Density 0.000%

    No Known Activations