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

    Neuronpedia

    INDEX
    Explanations

    thrilled to announce or express excitement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    1.41
    가
    1.38
     ifs
    1.30
    ting
    1.28
    цца
    1.27
    лно
    1.27
    ა
    1.22
    요
    1.20
     πάντα
    1.20
    ست
    1.19
    POSITIVE LOGITS
    𝖆
    1.62
    ال
    1.61
    る
    1.58
    𝚊
    1.56
    ोर
    1.55
    पणे
    1.52
    ز
    1.48
    ة
    1.48
    લ
    1.48
     Dominguez
    1.40
    Act Density 0.001%

    No Known Activations