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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash

    The neuron responds to the word “class” (and its morphological variants like classes, classify, classification) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Hur
    -0.08
     Petro
    -0.08
     варі
    -0.07
     Ventura
    -0.07
     pivot
    -0.07
     венти
    -0.07
     Puerto
    -0.07
    .KeyEvent
    -0.07
     Petr
    -0.07
     öt
    -0.07
    POSITIVE LOGITS
     Class
    0.16
     class
    0.16
    Class
    0.15
     classes
    0.13
    _class
    0.13
    class
    0.13
    -class
    0.13
    CLASS
    0.12
    	class
    0.12
    (class
    0.12
    Act Density 0.091%

    No Known Activations