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

    Neuronpedia

    INDEX
    Explanations

    Asking questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    repair
    -0.06
    说
    -0.06
     продукты
    -0.06
     Canc
    -0.06
     Franç
    -0.06
    ão
    -0.06
     honda
    -0.06
     Detection
    -0.06
     obligated
    -0.06
     Centre
    -0.06
    POSITIVE LOGITS
     QTest
    0.06
     jeux
    0.06
    ndef
    0.06
    .
↵↵
    0.06
    setScale
    0.06
     ".↵
    0.06
    ongsTo
    0.06
    _deinit
    0.06
    .win
    0.06
    .destroy
    0.06
    Act Density 0.049%

    No Known Activations