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

    Neuronpedia

    INDEX
    Explanations

    Singles, doubles, GMV

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙔
    0.46
     Craigslist
    0.43
    maktadır
    0.43
    aikh
    0.43
    ▇
    0.41
     تكونوا
    0.39
    ला
    0.39
    ウェブ
    0.39
    ➷
    0.39
    mektedir
    0.38
    POSITIVE LOGITS
     Singles
    0.48
     doubles
    0.48
     gm
    0.46
     singles
    0.46
     GM
    0.46
    GM
    0.44
     সুইস
    0.43
    双
    0.40
     Double
    0.40
     двой
    0.39
    Act Density 0.005%

    No Known Activations