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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    issenschaft
    -0.07
     Wrest
    -0.06
    �
    -0.06
    誤
    -0.06
    ে
    -0.06
    ática
    -0.06
    泳
    -0.06
    /count
    -0.06
     면
    -0.05
     voyeur
    -0.05
    POSITIVE LOGITS
    -it
    0.07
     Tabs
    0.07
    _lua
    0.07
    umni
    0.06
    Sig
    0.06
     searcher
    0.06
     Shooter
    0.06
    =username
    0.06
    larınız
    0.06
     centered
    0.06
    Act Density 0.003%

    No Known Activations