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

    Neuronpedia

    INDEX
    Explanations

    Code, getting status

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    neider
    -0.07
    帅哥
    -0.07
    _ra
    -0.07
    _service
    -0.07
    	create
    -0.07
    欻
    -0.06
    uge
    -0.06
    ”:
    -0.06
     agregar
    -0.06
     sending
    -0.06
    POSITIVE LOGITS
     Rolling
    0.07
    Labels
    0.07
    坚实的
    0.07
    }elseif
    0.07
     Nylon
    0.07
    갠
    0.06
     Sites
    0.06
    тики
    0.06
     unmarried
    0.06
    深
    0.06
    Act Density 0.046%

    No Known Activations