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

    Neuronpedia

    INDEX
    Explanations

    information orrepetitions of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     स्ट्र
    0.43
    住宿
    0.42
    াইড
    0.40
     ASU
    0.39
    俬
    0.39
     integração
    0.38
     Österreich
    0.38
    斯拉
    0.38
     मीटर
    0.38
     हायर
    0.38
    POSITIVE LOGITS
     commits
    0.48
    format
    0.47
     releases
    0.46
    eea
    0.46
     srd
    0.45
    editor
    0.45
    rtc
    0.44
    듕
    0.44
    output
    0.43
    ivable
    0.43
    Act Density 0.006%

    No Known Activations