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

    Neuronpedia

    INDEX
    Explanations

    percentage with asterisk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emery
    0.44
     his
    0.41
    okat
    0.41
    ]，
    0.41
     sprouts
    0.39
    >
    0.38
     a
    0.38
     sebagainya
    0.37
    bts
    0.37
    ]].
    0.37
    POSITIVE LOGITS
     (*)
    0.59
     (*
    0.59
     *(
    0.59
     **,
    0.58
    *,
    0.57
     (**
    0.55
    **,
    0.53
    *)
    0.50
    \*
    0.50
     $*$
    0.50
    Act Density 0.001%

    No Known Activations