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

    Neuronpedia

    INDEX
    Explanations

    code and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    깨
    -0.07
     Regions
    -0.07
    	cell
    -0.06
     biçim
    -0.06
    기의
    -0.06
    .Results
    -0.06
     nn
    -0.06
    _Max
    -0.06
    Parts
    -0.06
     totalPrice
    -0.06
    POSITIVE LOGITS
    했습니다
    0.07
    "\↵
    0.06
    veyor
    0.06
    TouchUpInside
    0.06
    ";//
    0.06
    承
    0.06
    irk
    0.06
     کند
    0.06
    \\"
    0.06
    бол
    0.06
    Act Density 0.014%

    No Known Activations