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

    Neuronpedia

    INDEX
    Explanations

    Exceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ával
    -0.07
    INDOW
    -0.07
     elementary
    -0.06
     visionary
    -0.06
    ATEST
    -0.06
     logger
    -0.06
    faculty
    -0.06
     سه
    -0.06
     santa
    -0.06
    	print
    -0.06
    POSITIVE LOGITS
    _encrypt
    0.07
    Ệ
    0.06
     strengthened
    0.06
     verge
    0.06
    mpl
    0.06
     evade
    0.06
     kanı
    0.06
    !!!!!
    0.06
     Ignore
    0.06
     insanın
    0.06
    Act Density 0.002%

    No Known Activations