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

    Neuronpedia

    INDEX
    Explanations

    Class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     systematically
    -0.07
    _None
    -0.07
     gently
    -0.07
     ACTIONS
    -0.06
    间
    -0.06
    	cd
    -0.06
    इन
    -0.06
     prevented
    -0.06
     Ab
    -0.06
     ayud
    -0.06
    POSITIVE LOGITS
    Class
    0.33
    _Class
    0.09
    	Class
    0.08
    getClass
    0.07
    CLASS
    0.07
    .createClass
    0.07
     UClass
    0.07
    FromClass
    0.06
    .getClassName
    0.06
     getClass
    0.06
    Act Density 0.005%

    No Known Activations