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

    Neuronpedia

    INDEX
    Explanations

    copyright, legal issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sedan
    -0.08
     mogą
    -0.07
    [mask
    -0.07
    	on
    -0.07
     interpolated
    -0.07
     amnesty
    -0.07
    ầ
    -0.06
    baar
    -0.06
    excel
    -0.06
     container
    -0.06
    POSITIVE LOGITS
    _Native
    0.07
     kald
    0.06
     let
    0.06
     Yosh
    0.06
    产学研
    0.06
    中方
    0.06
    찎
    0.06
    физическ
    0.06
    锊
    0.06
    .Mod
    0.06
    Act Density 0.001%

    No Known Activations