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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dangerously
    -0.06
    _render
    -0.06
     legalize
    -0.06
     defendant
    -0.06
     Suspension
    -0.06
    sit
    -0.06
    .mar
    -0.06
     chuyên
    -0.06
     Shr
    -0.06
     intervals
    -0.06
    POSITIVE LOGITS
    ViewSet
    0.07
    restart
    0.07
    	rb
    0.06
     vulnerabilities
    0.06
    scriber
    0.06
    conomics
    0.06
    eced
    0.06
     guardian
    0.06
    resultSet
    0.06
    (typeof
    0.06
    Act Density 0.005%

    No Known Activations