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

    Neuronpedia

    INDEX
    Explanations

    yarn crafts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    datos
    1.75
    SXml
    1.53
    ᡳ
    1.48
     gesamte
    1.45
    deki
    1.45
    không
    1.44
     ganze
    1.41
    dengan
    1.38
     intending
    1.36
    oad
    1.34
    POSITIVE LOGITS
    ات
    1.73
    ت
    1.71
    s
    1.61
    ের
    1.55
    ان
    1.51
    ς
    1.45
    N
    1.41
    ים
    1.37
    ਆਂ
    1.31
    تون
    1.28
    Act Density 0.009%

    No Known Activations