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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <State
    -0.07
    toy
    -0.06
    	camera
    -0.06
     viewController
    -0.06
    	ps
    -0.06
     Experienced
    -0.06
    _accuracy
    -0.06
     ESC
    -0.06
    "x
    -0.06
    %C
    -0.06
    POSITIVE LOGITS
     reader
    0.07
    ectors
    0.06
    ocup
    0.06
    weet
    0.06
    شار
    0.06
    mise
    0.06
    abwe
    0.06
     thickness
    0.06
    테
    0.06
    ими
    0.06
    Act Density 0.006%

    No Known Activations