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

    Neuronpedia

    INDEX
    Explanations

    variable assignment with "="

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =
    1.11
    ]=
    1.08
    }=
    1.08
    |=
    1.07
    --
    1.04
    —-
    0.94
    ="
    0.93
    --“
    0.90
    —“
    0.88
    >=
    0.88
    POSITIVE LOGITS
     ::
    1.11
     ...,
    1.11
     +,
    1.09
     !,
    1.05
     -,
    1.02
     …,
    1.00
     :,
    1.00
     ..,
    0.99
     &,
    0.97
     +
    0.95
    Act Density 0.007%

    No Known Activations