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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     languages
    -0.07
    отя
    -0.07
    项目
    -0.07
     дра
    -0.07
     eben
    -0.06
    _minutes
    -0.06
    UTTON
    -0.06
    平方
    -0.06
    feature
    -0.06
    可是
    -0.06
    POSITIVE LOGITS
    	RuntimeObject
    0.07
    _slot
    0.06
     forest
    0.06
    .clear
    0.06
     thickness
    0.06
     valued
    0.06
    *)"
    0.06
    ++;
    0.06
    念
    0.06
    ension
    0.06
    Act Density 0.003%

    No Known Activations