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

    Neuronpedia

    INDEX
    Explanations

    travel planning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     steward
    -0.08
    Bur
    -0.07
     unarmed
    -0.06
    -utils
    -0.06
    Josh
    -0.06
    Focused
    -0.06
     orgy
    -0.06
    _timeout
    -0.06
    URE
    -0.06
    .exit
    -0.06
    POSITIVE LOGITS
    특별시
    0.07
    	Route
    0.07
    rip
    0.06
    etSocketAddress
    0.06
    ıyorum
    0.06
    nodiscard
    0.06
     Tal
    0.06
     сбор
    0.06
     عوامل
    0.06
    .Light
    0.06
    Act Density 0.037%

    No Known Activations