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

    Neuronpedia

    INDEX
    Explanations

    a little more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Slightly
    1.56
     slightly
    1.46
     sommige
    1.30
    slightly
    1.29
     слегка
    1.28
     매우
    1.28
     অত্যন্ত
    1.25
     ligeramente
    1.24
     somewhat
    1.23
    なかなか
    1.22
    POSITIVE LOGITS
     bit
    1.20
    씩
    1.16
     more
    1.09
     leeway
    1.07
     ado
    1.03
     else
    1.01
     less
    1.01
     longer
    0.99
    чис
    0.97
     fanfare
    0.97
    Act Density 0.174%

    No Known Activations