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

    Neuronpedia

    INDEX
    Explanations

    Directions and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GO
    -0.07
     Holy
    -0.06
    ्ल
    -0.06
    diff
    -0.06
     holy
    -0.06
     compound
    -0.06
    rafted
    -0.06
    DER
    -0.06
    primary
    -0.06
     умер
    -0.06
    POSITIVE LOGITS
     آنها
    0.07
    Fal
    0.07
     thân
    0.06
    (Transaction
    0.06
    NotExist
    0.06
    中华
    0.06
    orda
    0.06
     Česko
    0.06
     Hond
    0.06
    QObject
    0.06
    Act Density 0.000%

    No Known Activations