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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Treasurer
    -0.08
    Twig
    -0.06
     eternal
    -0.06
    Kenn
    -0.06
     цель
    -0.06
    arer
    -0.06
     Dmit
    -0.06
    METHOD
    -0.06
     ZEND
    -0.06
     terrorism
    -0.06
    POSITIVE LOGITS
    inar
    0.07
    ISIBLE
    0.06
    าน
    0.06
    Conv
    0.06
    美
    0.06
    ΗΜΑ
    0.06
     SMART
    0.06
    нят
    0.06
    metric
    0.06
    _SERIAL
    0.06
    Act Density 0.002%

    No Known Activations