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

    Neuronpedia

    INDEX
    Explanations

    intent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    帷
    -0.08
     depart
    -0.07
    迅猛
    -0.07
     dear
    -0.07
     oss
    -0.07
    /tags
    -0.07
    挣
    -0.07
     web
    -0.07
    孤
    -0.07
    络
    -0.07
    POSITIVE LOGITS
    修剪
    0.08
    拃
    0.07
    amaged
    0.07
    "It
    0.07
    _integral
    0.07
     zamówienia
    0.07
     offence
    0.07
    폅
    0.07
    走廊
    0.07
     nếu
    0.07
    Act Density 0.001%

    No Known Activations