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

    Neuronpedia

    INDEX
    Explanations

    business needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    1.61
     big
    1.39
     both
    1.35
     date
    1.31
     note
    1.31
    ↵
    1.30
     large
    1.30
     bitmaps
    1.30
     one
    1.30
    dated
    1.26
    POSITIVE LOGITS
    ísk
    1.34
    τούν
    1.28
     Cambio
    1.22
     akik
    1.22
    <unused1874>
    1.21
    ‮
    1.18
    ໍ
    1.14
     Полу
    1.14
     profiss
    1.13
    ໃ
    1.13
    Act Density 0.387%

    No Known Activations