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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Leonard
    -0.08
    ав
    -0.07
     parsley
    -0.07
    uC
    -0.07
     engraved
    -0.07
     toc
    -0.07
     Enum
    -0.06
    veal
    -0.06
     bầu
    -0.06
     ти
    -0.06
    POSITIVE LOGITS
     перел
    0.06
    (cell
    0.06
    abase
    0.06
     เห
    0.06
    _feats
    0.06
    ohn
    0.06
    lpVtbl
    0.06
    =params
    0.06
    (score
    0.06
     Ö
    0.06
    Act Density 0.002%

    No Known Activations