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

    Neuronpedia

    INDEX
    Explanations

    phrases followed by acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _*
    0.82
    ≃
    0.80
    ，《
    0.78
    *_
    0.77
     <!--<
    0.76
    、《
    0.75
     Архивировано
    0.74
    నున్న
    0.73
    ：《
    0.73
    ≥
    0.72
    POSITIVE LOGITS
     (
    1.21
    (
    1.01
    简称
    1.01
     abbreviated
    1.01
    ͑
    0.87
     acronym
    0.83
    thane
    0.78
    (")
    0.74
    \(
    0.74
     aka
    0.73
    Act Density 0.650%

    No Known Activations