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

    Neuronpedia

    INDEX
    Explanations

    address

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ould
    -0.06
     tractor
    -0.06
    แท
    -0.06
    arshal
    -0.06
    播
    -0.06
    ์บ
    -0.06
    yon
    -0.06
    lide
    -0.06
    _over
    -0.06
     Worship
    -0.06
    POSITIVE LOGITS
     các
    0.07
     наст
    0.07
     `↵
    0.07
    .syntax
    0.07
    .scalar
    0.07
     форми
    0.07
     物
    0.06
     membuat
    0.06
     Muhammad
    0.06
     thuộc
    0.06
    Act Density 0.020%

    No Known Activations