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

    Neuronpedia

    INDEX
    Explanations

    wrote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .layouts
    -0.08
     prejudice
    -0.07
    _deep
    -0.07
    _hz
    -0.06
     Rahmen
    -0.06
    ptoms
    -0.06
    .assertj
    -0.06
     prison
    -0.06
     Canadians
    -0.06
     CMD
    -0.06
    POSITIVE LOGITS
    �
    0.07
     says
    0.06
    овал
    0.06
    精
    0.06
     concerts
    0.06
    vlc
    0.06
    didn
    0.06
     عب
    0.06
     WANT
    0.06
     �
    0.06
    Act Density 0.006%

    No Known Activations