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

    Neuronpedia

    INDEX
    Explanations

    equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	files
    -0.07
    .printf
    -0.07
     assertions
    -0.07
    .nanoTime
    -0.06
     Sri
    -0.06
     motel
    -0.06
    Macro
    -0.06
    辍
    -0.06
    discover
    -0.06
    _tar
    -0.06
    POSITIVE LOGITS
    效应
    0.07
    chartInstance
    0.07
    -end
    0.07
     кажется
    0.07
    dzą
    0.07
     tendencies
    0.07
     Deals
    0.07
    とか
    0.06
     Common
    0.06
    不一样
    0.06
    Act Density 0.001%

    No Known Activations