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

    Neuronpedia

    INDEX
    Explanations

    uh, um, yeah

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     др
    0.50
     ২টি
    0.46
     उत्तरप्रदेश
    0.45
     সরকারী
    0.45
     ½
    0.44
     ৮ম
    0.44
     ¼
    0.43
     परन्तु
    0.42
     НЕ
    0.42
     গ্রহন
    0.41
    POSITIVE LOGITS
     uh
    1.32
     ähm
    1.30
     Yeah
    1.08
     um
    0.98
     äh
    0.96
     보면은
    0.96
    Yeah
    0.95
     yeah
    0.93
    呃
    0.93
     Uh
    0.89
    Act Density 0.058%

    No Known Activations