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

    Neuronpedia

    INDEX
    Explanations

    Russian language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deals
    -0.07
     Doyle
    -0.07
     modelBuilder
    -0.07
    abstract
    -0.07
    .bulk
    -0.06
    )).
    -0.06
     obliv
    -0.06
    +.
    -0.06
    &display
    -0.06
    _spot
    -0.06
    POSITIVE LOGITS
     Partisi
    0.07
    silent
    0.07
    �
    0.07
    相当
    0.07
     Riot
    0.06
    że
    0.06
    етом
    0.06
     :＼
    0.06
    字符
    0.06
     tão
    0.06
    Act Density 0.133%

    No Known Activations