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

    Neuronpedia

    INDEX
    Explanations

    confidential information disclosed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    应急
    0.42
     uncover
    0.39
     Josephson
    0.39
    ियोग्राफी
    0.39
     pendekatan
    0.39
     Harrier
    0.39
    midrule
    0.38
     herein
    0.38
    alek
    0.38
     Grafik
    0.37
    POSITIVE LOGITS
    ATM
    0.43
    フ
    0.42
    人と
    0.40
    它的
    0.39
    同じ
    0.39
    [&
    0.39
    Strip
    0.39
    話し
    0.39
    0.38
    چی
    0.38
    Act Density 0.000%

    No Known Activations