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
     Endpoint
    -0.07
     euro
    -0.07
     Never
    -0.07
     pivot
    -0.07
     Nep
    -0.07
     Verg
    -0.07
     pity
    -0.07
     Soviet
    -0.07
    oti
    -0.07
    Hur
    -0.07
    POSITIVE LOGITS
     Class
    0.17
    Class
    0.16
     class
    0.16
    _class
    0.16
    class
    0.14
     classes
    0.13
    -class
    0.13
    	Class
    0.13
    (Class
    0.12
    	class
    0.12
    Act Density 0.074%

    No Known Activations