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

    Neuronpedia

    INDEX
    Explanations

    character replacement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    园
    -0.07
     positivity
    -0.07
     영
    -0.07
     DEFAULT
    -0.06
     já
    -0.06
    幼
    -0.06
    گانی
    -0.06
     ندارد
    -0.06
     proto
    -0.06
     Peg
    -0.06
    POSITIVE LOGITS
    	of
    0.07
    .standard
    0.07
     Constructor
    0.07
    ,'
    0.07
    opyright
    0.07
    accordion
    0.06
     doe
    0.06
    675
    0.06
     reigning
    0.06
    .getInstance
    0.06
    Act Density 0.003%

    No Known Activations