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

    Neuronpedia

    INDEX
    Explanations

    same subjects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    internal
    -0.07
    EOS
    -0.07
    long
    -0.06
     Yak
    -0.06
     harming
    -0.06
     صورت
    -0.06
     інозем
    -0.06
     رئیس
    -0.06
     defiant
    -0.06
    SUP
    -0.06
    POSITIVE LOGITS
     POSSIBILITY
    0.07
     LGPL
    0.06
    	Node
    0.06
     DateFormat
    0.06
    iphers
    0.06
     criticize
    0.06
    	union
    0.06
     Applicants
    0.06
     ModelAndView
    0.06
     SET
    0.06
    Act Density 0.131%

    No Known Activations