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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Semantic
    -0.08
    _front
    -0.07
    .middle
    -0.07
    창
    -0.07
    [table
    -0.07
    _Internal
    -0.07
    [out
    -0.07
    <Test
    -0.07
    南山
    -0.07
    殣
    -0.06
    POSITIVE LOGITS
    iddleware
    0.07
    >\
    0.07
     inhibitors
    0.07
    arius
    0.06
    bler
    0.06
    ﭬ
    0.06
    それぞれ
    0.06
     emphas
    0.06
    userId
    0.06
    说明
    0.06
    Act Density 0.001%

    No Known Activations