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

    Neuronpedia

    INDEX
    Explanations

    code data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     packageName
    0.54
    packageName
    0.44
     TestAvg
    0.44
    BuildConfig
    0.43
    সঙ্ঘ
    0.43
    暱
    0.41
    PACKAGE
    0.40
    Okno
    0.40
    Django
    0.39
     قانونی
    0.38
    POSITIVE LOGITS
     area
    0.49
     amen
    0.43
     bottom
    0.41
     bi
    0.40
     board
    0.40
     boron
    0.39
     feed
    0.39
     Cook
    0.38
     approval
    0.38
     amendment
    0.38
    Act Density 0.000%

    No Known Activations