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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     נולד
    -0.07
    _radius
    -0.07
    MH
    -0.07
    _Params
    -0.07
    _shapes
    -0.06
    강
    -0.06
    基础
    -0.06
    .PER
    -0.06
    door
    -0.06
    込まれ
    -0.06
    POSITIVE LOGITS
    _hard
    0.07
     artikel
    0.07
    逵
    0.06
    毕
    0.06
     lengthy
    0.06
    	win
    0.06
     squirrel
    0.06
     serviços
    0.06
    اقل
    0.06
    linewidth
    0.06
    Act Density 0.023%

    No Known Activations