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

    Neuronpedia

    INDEX
    Explanations

    Stack Overflow links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cũ
    -0.07
     hands
    -0.07
    "path
    -0.06
    기가
    -0.06
    _weather
    -0.06
    	points
    -0.06
    低
    -0.06
    supply
    -0.06
    写
    -0.06
    번호
    -0.06
    POSITIVE LOGITS
     pride
    0.07
     ----------------------------------------------------------------------↵
    0.07
    	val
    0.07
    resources
    0.06
     delimiter
    0.06
    _LL
    0.06
    -lang
    0.06
    (TEXT
    0.06
    /column
    0.06
    Iter
    0.06
    Act Density 0.003%

    No Known Activations