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
     Tob
    -0.08
    (aa
    -0.08
     обучения
    -0.07
     Ng
    -0.07
     Independent
    -0.07
    (Page
    -0.07
    苛
    -0.07
     appeals
    -0.07
    Unexpected
    -0.07
    زواج
    -0.07
    POSITIVE LOGITS
    nette
    0.07
     $("<
    0.07
    (disposing
    0.07
    irate
    0.07
    �
    0.06
    EMPL
    0.06
    .setColumns
    0.06
    \",↵
    0.06
     getHeight
    0.06
    הור
    0.06
    Act Density 0.048%

    No Known Activations