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

    Neuronpedia

    INDEX
    Explanations

    as clause introducer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ไม่ใช่
    0.52
     Assignments
    0.50
     Passport
    0.49
     বলছেন
    0.49
     है
    0.47
    那时
    0.47
     thường
    0.46
     Including
    0.46
     causando
    0.45
     Because
    0.45
    POSITIVE LOGITS
    depos
    0.53
    took
    0.50
    dozen
    0.48
    dye
    0.48
     tries
    0.47
    ጼ
    0.47
    全体
    0.46
    ス
    0.45
    ས
    0.45
     pours
    0.45
    Act Density 0.019%

    No Known Activations