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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     and
    -0.12
     und
    -0.10
     And
    -0.10
     AND
    -0.10
    'https
    -0.08
     گردش
    -0.08
     &
    -0.08
     along
    -0.07
    Impossible
    -0.07
     και
    -0.07
    POSITIVE LOGITS
    ,,,,,,,,
    0.06
    .getCell
    0.06
     Automobile
    0.06
    ск
    0.06
    ,type
    0.06
     Lockheed
    0.06
    Alternate
    0.06
    стру
    0.06
    Contract
    0.05
     klu
    0.05
    Act Density 0.157%

    No Known Activations