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

    Neuronpedia

    INDEX
    Explanations

    `?` and code injection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ையாக
    0.43
    掍
    0.41
    вок
    0.40
     तहरीर
    0.39
    0.39
    瓠
    0.39
    ﮩ
    0.38
    㮆
    0.38
    🙏🙏
    0.38
    ணமாக
    0.37
    POSITIVE LOGITS
     ?
    2.34
    ?
    2.16
    ?,
    2.13
    ？
    2.13
    ?.
    2.03
    ?)
    2.00
    ?"
    1.98
     ?,
    1.98
    ?-
    1.98
    ?;
    1.97
    Act Density 0.080%

    No Known Activations