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

    Neuronpedia

    INDEX
    Explanations

    Pronouns and system descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jm
    -0.06
     luc
    -0.06
     xe
    -0.06
    .target
    -0.06
    .helper
    -0.06
    mix
    -0.06
    글
    -0.06
    LOG
    -0.06
    _degree
    -0.06
    game
    -0.06
    POSITIVE LOGITS
    izontally
    0.07
    okino
    0.07
    아파트
    0.07
     Ihren
    0.07
    INFRINGEMENT
    0.07
     weekends
    0.06
    оск
    0.06
     применения
    0.06
     Operational
    0.06
     unsure
    0.06
    Act Density 0.103%

    No Known Activations