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

    Neuronpedia

    INDEX
    Explanations

    if, exchange, process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    硙
    0.35
    Macrophages
    0.31
    েলের
    0.30
    ंचाई
    0.30
    𝚢
    0.30
    valueOf
    0.30
    淝
    0.30
    র্জাতিক
    0.29
    ائیگی
    0.29
    ForSettings
    0.29
    POSITIVE LOGITS
    ine
    0.33
    .
    0.31
     E
    0.30
     -
    0.30
     "
    0.29
    ita
    0.29
    ,
    0.29
    -
    0.29
     Z
    0.28
     J
    0.28
    Act Density 0.000%

    No Known Activations