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

    Neuronpedia

    INDEX
    Explanations

    subsequently, began, then, thereafter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     functionally
    0.27
    Algorithm
    0.26
     algorithm
    0.26
    ですので
    0.25
     algorithmic
    0.25
     readability
    0.25
     λό
    0.25
     specif
    0.25
     cookbooks
    0.25
     interoper
    0.24
    POSITIVE LOGITS
     Subsequently
    0.32
     Soon
    0.31
     began
    0.31
     Kemudian
    0.30
     comenzaron
    0.30
     comenzó
    0.30
     kemudian
    0.30
     Gradually
    0.30
    後來
    0.29
     Thereafter
    0.29
    Act Density 0.171%

    No Known Activations