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

    Neuronpedia

    INDEX
    Explanations

    women's achievements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    藁
    -0.08
    ﮢ
    -0.08
    鉴
    -0.07
    MIT
    -0.07
    -INFRINGEMENT
    -0.07
    元旦
    -0.07
    大爷
    -0.07
     Morg
    -0.07
    뀝
    -0.07
     disclosures
    -0.07
    POSITIVE LOGITS
     flashing
    0.08
     antennas
    0.07
    ечно
    0.07
    Az
    0.07
     Psalm
    0.07
     Compiler
    0.07
     Byte
    0.07
    ("../
    0.07
    عقل
    0.07
     Chest
    0.06
    Act Density 0.160%

    No Known Activations