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

    Neuronpedia

    INDEX
    Explanations

    start of code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    人性
    0.58
     nostri
    0.58
    路的
    0.57
     poesía
    0.56
    ية
    0.55
    á
    0.55
    resTmp
    0.55
     Derbyshire
    0.55
     á
    0.54
     homophobic
    0.54
    POSITIVE LOGITS
    (
    0.72
    Everyone
    0.55
    Many
    0.52
    courses
    0.50
    GOB
    0.50
    for
    0.50
     روی
    0.49
    picode
    0.49
    an
    0.48
    ROS
    0.48
    Act Density 0.000%

    No Known Activations