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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    udded
    -0.07
    _once
    -0.07
    揭开
    -0.07
     GOODS
    -0.07
    干什么
    -0.07
    Stroke
    -0.07
    BLEM
    -0.06
    ulg
    -0.06
     comes
    -0.06
     Blender
    -0.06
    POSITIVE LOGITS
     trab
    0.07
    코
    0.07
     Winning
    0.07
     shallow
    0.07
     flavors
    0.07
    理念
    0.06
     bouquet
    0.06
    彪
    0.06
    ATEGORY
    0.06
    ontology
    0.06
    Act Density 0.001%

    No Known Activations