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

    Neuronpedia

    INDEX
    Explanations

    core principles, as defined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ได้
    0.64
     nhưng
    0.61
    <0x91>
    0.59
     fotografía
    0.58
     l
    0.55
     không
    0.55
     worden
    0.54
    <0xBE>
    0.54
     لكن
    0.54
    <0xAF>
    0.53
    POSITIVE LOGITS
    a
    0.60
    지
    0.59
    as
    0.58
    प
    0.57
    ק
    0.57
    is
    0.56
     alliances
    0.53
    ッテリー
    0.53
    in
    0.52
     imbalances
    0.52
    Act Density 0.193%

    No Known Activations