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
     edges
    -0.06
    ไร
    -0.06
    wood
    -0.06
    adelphia
    -0.06
     Germany
    -0.06
    وده
    -0.06
     lights
    -0.06
    448
    -0.06
    หาร
    -0.06
    िष
    -0.06
    POSITIVE LOGITS
    _DX
    0.07
    BOOK
    0.07
    StateChanged
    0.07
     alış
    0.07
    صات
    0.07
    iture
    0.06
    unately
    0.06
    .nii
    0.06
    	api
    0.06
    っ�
    0.06
    Act Density 0.008%

    No Known Activations