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

    Neuronpedia

    INDEX
    Explanations

    code, VHDL, OCaml

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     danam
    0.43
    aacute
    0.39
    esters
    0.38
     исто
    0.36
     satd
    0.36
     looting
    0.35
     volunt
    0.35
     }//
    0.35
     Lour
    0.35
    ेप
    0.35
    POSITIVE LOGITS
    --
    0.59
     --
    0.57
    {-#
    0.53
    {-
    0.52
    module
    0.48
    ("--
    0.47
    ----------------
    0.45
     `--
    0.45
    (--
    0.44
     '--
    0.42
    Act Density 0.021%

    No Known Activations