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

    Neuronpedia

    INDEX
    Explanations

    words starting with str

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PG
    0.41
     MAIL
    0.40
     Clubhouse
    0.40
    ]).
    0.39
    ์
    0.39
    dll
    0.38
     Examiners
    0.38
    ية
    0.38
     Estate
    0.38
     Uit
    0.38
    POSITIVE LOGITS
     스트
    0.93
     スト
    0.74
     স্ট্র
    0.72
     स्ट्र
    0.71
     str
    0.71
     stre
    0.71
     Стре
    0.69
     стре
    0.66
     stret
    0.64
    Stre
    0.64
    Act Density 0.063%

    No Known Activations