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

    Neuronpedia

    INDEX
    Explanations

    the [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лас
    1.32
    ли
    1.30
    iz
    1.22
    ox
    1.13
    stion
    1.13
    িন
    1.12
     efficient
    1.10
    िया
    1.09
    亠
    1.06
     coch
    1.05
    POSITIVE LOGITS
     परंतु
    1.29
     Однако
    1.25
     그러나
    1.23
     поскольку
    1.22
     हालांकि
    1.20
     svojim
    1.19
    iéndose
    1.18
    ﺽ
    1.18
     בין
    1.17
    ﺵ
    1.16
    Act Density 0.249%

    No Known Activations