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

    Neuronpedia

    INDEX
    Explanations

    room

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stretches
    -0.07
    icích
    -0.07
     kıs
    -0.07
     영어
    -0.06
    ーナ
    -0.06
    され
    -0.06
    ﺔ
    -0.06
     Sanders
    -0.06
     Tor
    -0.06
    Args
    -0.06
    POSITIVE LOGITS
     {})↵
    0.08
    .innerHTML
    0.07
     ambient
    0.07
     backlight
    0.07
    (dialog
    0.07
    $res
    0.06
    _AC
    0.06
     Estados
    0.06
    <Document
    0.06
     prem
    0.06
    Act Density 0.002%

    No Known Activations