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

    Neuronpedia

    INDEX
    Explanations

    output format and generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onClick
    1.30
    ęg
    1.29
     ẹ
    1.29
    ل
    1.22
    l
    1.21
     собой
    1.18
     jsonData
    1.17
    níci
    1.16
    at
    1.13
    िफिशियल
    1.11
    POSITIVE LOGITS
    ted
    1.34
    ts
    1.21
    வே
    1.20
    ses
    1.10
    ting
    1.09
    মূ
    1.08
    shire
    1.07
    ز
    1.04
    ta
    1.04
    🏼
    1.04
    Act Density 0.120%

    No Known Activations