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

    Neuronpedia

    INDEX
    Explanations

    vector database

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x0D>
    0.63
    0
    0.58
    ש
    0.53
    <0x80>
    0.53
    出して
    0.49
    持って
    0.48
    他的
    0.47
    のです
    0.47
    니다
    0.47
    搅
    0.47
    POSITIVE LOGITS
    એસ
    0.69
     assegn
    0.66
     découverte
    0.64
    ﺔ
    0.62
    ಎಸ್
    0.58
     <!--<
    0.57
     estabelecimento
    0.57
     começ
    0.56
     difficoltà
    0.56
    എസ്
    0.55
    Act Density 0.031%

    No Known Activations