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

    Neuronpedia

    INDEX
    Explanations

    width height

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /xml
    -0.07
    虎
    -0.06
    Analyzer
    -0.06
    Folders
    -0.06
     realization
    -0.06
    flush
    -0.06
    _container
    -0.06
    _node
    -0.06
    _CBC
    -0.06
     cancer
    -0.06
    POSITIVE LOGITS
     ；
    0.06
     نک
    0.06
     soy
    0.06
    ίθ
    0.06
    —if
    0.06
     belirtilen
    0.06
     تا
    0.06
     Glad
    0.06
     Kn
    0.06
    .then
    0.06
    Act Density 0.021%

    No Known Activations