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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     matière
    -0.09
    ક્ટ
    -0.09
     entrepreneurial
    -0.09
    လာ
    -0.09
     טיפול
    -0.09
     compatibility
    -0.08
     צע
    -0.08
    Maison
    -0.08
     vocation
    -0.08
     חלק
    -0.08
    POSITIVE LOGITS
     conceded
    0.11
     innings
    0.10
     remporté
    0.10
     remport
    0.10
     opponent
    0.10
     vitória
    0.09
     विजय
    0.09
     árbit
    0.09
    Opponent
    0.09
     경기
    0.09
    Act Density 0.122%

    No Known Activations