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

    Neuronpedia

    INDEX
    Explanations

    words following titles or specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ב
    1.03
     Validación
    0.95
     Virology
    0.93
    ور
    0.92
    Мі
    0.92
    槛
    0.91
     Seguridad
    0.91
     trasera
    0.91
    ୃ
    0.90
     Apostolic
    0.90
    POSITIVE LOGITS
     one
    0.88
    たとえば
    0.88
     club
    0.75
     дня
    0.74
    ого
    0.73
    O
    0.73
    n
    0.72
     д
    0.70
    to
    0.70
     doc
    0.70
    Act Density 0.002%

    No Known Activations