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

    Neuronpedia

    INDEX
    Explanations

    examples in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eenth
    1.37
    term
    1.17
    áneo
    1.17
    orra
    1.15
    كيل
    1.14
    umento
    1.13
    arithmic
    1.12
    urato
    1.11
    THING
    1.09
     érdekében
    1.08
    POSITIVE LOGITS
    들과
    1.45
    들에게
    1.43
    들을
    1.43
    들도
    1.39
    들이
    1.37
     wallpapers
    1.34
    டுகளை
    1.33
    들에
    1.33
    들은
    1.31
    ኖች
    1.29
    Act Density 0.148%

    No Known Activations