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

    Neuronpedia

    INDEX
    Explanations

    swap usage and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    通用
    0.43
     ○
    0.41
     মূল
    0.39
     beragam
    0.38
    がん
    0.38
    埶
    0.37
    டுதல்
    0.37
     ભૂ
    0.37
    悳
    0.37
     мере
    0.36
    POSITIVE LOGITS
     SW
    0.83
     Swap
    0.68
    SW
    0.67
     Sw
    0.65
    Sw
    0.64
     sw
    0.63
     swap
    0.62
    Swap
    0.62
     swapped
    0.60
     swapping
    0.59
    Act Density 0.016%

    No Known Activations