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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     red
    -0.08
     impres
    -0.07
    venue
    -0.07
    人脸识别
    -0.07
     supérieur
    -0.07
     breach
    -0.07
    _inverse
    -0.07
    שוקולד
    -0.07
    RoleId
    -0.07
    鹠
    -0.07
    POSITIVE LOGITS
     rapidly
    0.08
    successful
    0.07
     beginning
    0.07
    嫡
    0.07
     wel
    0.07
     neatly
    0.06
    	parser
    0.06
     profitable
    0.06
     hes
    0.06
     contaminants
    0.06
    Act Density 0.011%

    No Known Activations