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

    Neuronpedia

    INDEX
    Explanations

    */

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     norms
    -0.07
     Req
    -0.06
    Simply
    -0.06
    "};↵
    -0.06
    Sans
    -0.06
     isolate
    -0.06
    -quote
    -0.06
     z
    -0.06
    훈
    -0.06
     Fiber
    -0.06
    POSITIVE LOGITS
    生命
    0.07
    าภ
    0.07
    _auc
    0.07
     propor
    0.06
    .payment
    0.06
    nr
    0.06
    CCR
    0.06
     Nguyễn
    0.06
    KeyDown
    0.06
    وده
    0.06
    Act Density 0.015%

    No Known Activations