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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    购买
    -0.07
    Evaluate
    -0.07
     año
    -0.06
    Reports
    -0.06
     fille
    -0.06
     جست
    -0.06
    izzato
    -0.06
    NFL
    -0.06
     Haupt
    -0.06
     verse
    -0.06
    POSITIVE LOGITS
     buổi
    0.07
    _accessor
    0.06
    .collectionView
    0.06
     аг
    0.06
     maç
    0.06
     mocker
    0.06
     risky
    0.06
    .sys
    0.06
    시키
    0.06
    OTAL
    0.06
    Act Density 0.037%

    No Known Activations