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

    Neuronpedia

    INDEX
    Explanations

    computer standards/languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    الح
    -0.07
     facilities
    -0.07
     жен
    -0.07
    <Resource
    -0.06
    政策
    -0.06
     Communication
    -0.06
     Universities
    -0.06
    hta
    -0.06
     Facilities
    -0.06
     roster
    -0.06
    POSITIVE LOGITS
    bol
    0.07
     ModelState
    0.07
    _NUMBER
    0.07
    	constexpr
    0.06
    昭和
    0.06
     '=
    0.06
    (j
    0.06
     "</
    0.06
    ),"
    0.06
     Especially
    0.06
    Act Density 0.029%

    No Known Activations