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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     denying
    -0.06
    coe
    -0.06
     waving
    -0.06
     plethora
    -0.06
    .mkdirs
    -0.06
    	signal
    -0.06
     outbreaks
    -0.06
     pca
    -0.06
    preci
    -0.06
     odio
    -0.06
    POSITIVE LOGITS
     haft
    0.07
    (Account
    0.07
    rote
    0.06
     yüzde
    0.06
     Mechanics
    0.06
     mechanics
    0.06
    _surface
    0.06
    カテゴリ
    0.06
     EURO
    0.06
     regularization
    0.06
    Act Density 0.110%

    No Known Activations