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

    Neuronpedia

    INDEX
    Explanations

    specifying or enumerating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ：
    0.71
    :
    0.67
    \...
    0.64
    ,
    0.60
    ):
    0.60
    )।
    0.60
    ...
    0.58
     」,
    0.58
    ）：
    0.58
     ：
    0.58
    POSITIVE LOGITS
     including
    1.74
     especially
    1.54
     particularly
    1.46
     whether
    1.43
     namely
    1.31
    including
    1.28
     regardless
    1.27
     ranging
    1.19
     incluindo
    1.19
     включая
    1.18
    Act Density 1.375%

    No Known Activations