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

    Neuronpedia

    INDEX
    Explanations

    background

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Face
    -0.07
     Face
    -0.07
    Delete
    -0.06
     WHO
    -0.06
     rent
    -0.06
     ranks
    -0.06
     Trace
    -0.06
     bottled
    -0.06
    .Users
    -0.06
     Ship
    -0.06
    POSITIVE LOGITS
    background
    0.09
    ;background
    0.08
    (())↵
    0.07
    ↵↵↵↵↵↵↵
    0.07
     Background
    0.07
    .activation
    0.07
    	describe
    0.06
    	background
    0.06
     ButterKnife
    0.06
    itious
    0.06
    Act Density 0.005%

    No Known Activations