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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apers
    -0.06
    moil
    -0.06
     Svens
    -0.06
    .news
    -0.06
     раза
    -0.06
     gute
    -0.06
    ometers
    -0.06
     addObject
    -0.06
    其实
    -0.06
    alez
    -0.06
    POSITIVE LOGITS
     Beş
    0.07
     questions
    0.07
    _CA
    0.06
     >=
    0.06
    _CLI
    0.06
     coatings
    0.06
    luğu
    0.06
    )>=
    0.06
    MAL
    0.06
    epochs
    0.06
    Act Density 0.284%

    No Known Activations