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

    Neuronpedia

    INDEX
    Explanations

    з, с, російська, українська

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sometime
    0.68
    ZW
    0.67
     Remember
    0.67
    правление
    0.65
     unplanned
    0.65
     zp
    0.64
    Zw
    0.64
     SWOT
    0.63
    wd
    0.63
     svůj
    0.62
    POSITIVE LOGITS
    ﺠ
    0.81
    верну
    0.81
     இலக்கிய
    0.74
    nali
    0.73
    ASER
    0.71
    вався
    0.69
    ALE
    0.68
     camas
    0.68
     Gagn
    0.68
     mús
    0.68
    Act Density 0.075%

    No Known Activations