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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    妙
    -0.07
    /upload
    -0.06
    ray
    -0.06
    -part
    -0.06
    节
    -0.06
    arnation
    -0.06
     ISP
    -0.06
     Brothers
    -0.06
    生活
    -0.06
     anus
    -0.06
    POSITIVE LOGITS
    188
    0.06
    .appendTo
    0.06
     Mao
    0.06
     wiping
    0.06
     поруш
    0.06
    	controller
    0.06
    .Threading
    0.06
     внут
    0.06
    mars
    0.06
    Json
    0.06
    Act Density 0.033%

    No Known Activations