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

    Neuronpedia

    INDEX
    Explanations

    module export/import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    داء
    0.38
    ートル
    0.36
    esas
    0.36
    ERTY
    0.36
     увлека
    0.36
    !),
    0.36
    モー
    0.35
     snapping
    0.35
     Ila
    0.35
    !)
    0.35
    POSITIVE LOGITS
    exports
    0.79
     exports
    0.78
    Exports
    0.75
     Exports
    0.70
     export
    0.58
     Export
    0.58
     수출
    0.57
     exporting
    0.53
    Export
    0.50
     exportation
    0.48
    Act Density 0.000%

    No Known Activations