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

    Neuronpedia

    INDEX
    Explanations

    code syntax and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಯ
    2.32
    ೇಯ
    2.31
    笉
    2.22
    徊
    2.19
    ])),
    2.19
     Turns
    2.17
     slows
    2.16
     }-
    2.14
     []),
    2.13
     Higher
    2.12
    POSITIVE LOGITS
    र
    2.61
    ا
    2.44
    maktan
    2.38
    uak
    2.29
    er
    2.18
    eris
    2.17
    descriptors
    2.16
    atzen
    2.10
    uč
    2.07
    ا۔
    2.06
    Act Density 0.069%

    No Known Activations