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

    Neuronpedia

    INDEX
    Explanations

    punctuation/code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _namespace
    -0.06
    akhstan
    -0.06
    .lex
    -0.06
    REQUEST
    -0.06
    USERNAME
    -0.06
    _application
    -0.06
     stringByAppending
    -0.06
     Anime
    -0.06
    -word
    -0.06
     blue
    -0.06
    POSITIVE LOGITS
    ức
    0.09
     dreadful
    0.08
     đề
    0.07
     almaktadır
    0.07
    िसक
    0.07
     trava
    0.07
     relu
    0.06
    ellt
    0.06
    ensem
    0.06
    iev
    0.06
    Act Density 0.237%

    No Known Activations