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

    Neuronpedia

    INDEX
    Explanations

    prices and locations in urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ではありません
    0.37
    ژی
    0.34
     ಸದ
    0.34
     വിഭാഗ
    0.34
     săptăm
    0.34
     varphi
    0.33
     außergewöhn
    0.33
     newApproved
    0.33
    хом
    0.32
     దక్షి
    0.32
    POSITIVE LOGITS
     |
    0.41
     with
    0.39
     as
    0.39
     &
    0.38
     -
    0.37
     in
    0.36
     Sn
    0.36
     according
    0.35
     at
    0.35
     Unt
    0.33
    Act Density 0.001%

    No Known Activations