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

    Neuronpedia

    INDEX
    Explanations

    code constructs: comparison and assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    1.13
     d
    1.09
    }.
    1.02
    。
    1.02
    .
    0.94
    an
    0.93
    ،
    0.92
     subsequent
    0.91
     upang
    0.90
    r
    0.89
    POSITIVE LOGITS
    اي
    1.21
    פ
    0.96
    नहीं
    0.96
    ไม่
    0.95
    ২৮
    0.93
    ೩
    0.91
    秩序
    0.91
    מ
    0.91
    га
    0.91
     localidades
    0.91
    Act Density 0.207%

    No Known Activations