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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    higher
    -0.07
    initial
    -0.07
     consumed
    -0.06
    _OUT
    -0.06
    _WH
    -0.06
     dhe
    -0.06
    dragon
    -0.06
    定义
    -0.06
    �
    -0.06
    ouri
    -0.06
    POSITIVE LOGITS
     ابن
    0.07
     Rocket
    0.07
    评
    0.06
    md
    0.06
    .OrderBy
    0.06
                    
    0.06
    تها
    0.06
     Publish
    0.06
    parser
    0.06
    /Search
    0.06
    Act Density 0.119%

    No Known Activations