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

    Neuronpedia

    INDEX
    Explanations

    File formats and GUIDs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jButton
    -0.08
     ![
    -0.07
     unforgettable
    -0.07
    蛙
    -0.07
     zmq
    -0.07
    ⻄
    -0.07
    닮
    -0.07
     xhr
    -0.07
    🎄
    -0.07
    ig
    -0.07
    POSITIVE LOGITS
     produ
    0.06
    的情况
    0.06
    _parts
    0.06
     Dialogue
    0.06
    我一直
    0.06
     branded
    0.06
     consistently
    0.06
    -encoded
    0.06
     locale
    0.06
    漏洞
    0.06
    Act Density 0.007%

    No Known Activations