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

    Neuronpedia

    INDEX
    Explanations

    plus/minus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Mat
    -0.08
    اشت
    -0.07
     balk
    -0.07
    doctrine
    -0.06
    Ng
    -0.06
     슈
    -0.06
     solidarity
    -0.06
     segue
    -0.06
     chút
    -0.06
    aris
    -0.06
    POSITIVE LOGITS
    uncated
    0.07
     Crest
    0.07
    >>&
    0.06
     Yankee
    0.06
    "]["
    0.06
    !",
    0.06
    (_('
    0.06
     kvinnor
    0.06
     leases
    0.06
     alignSelf
    0.06
    Act Density 0.011%

    No Known Activations