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

    Neuronpedia

    INDEX
    Explanations

    Spanish question starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    閪
    1.35
     त्यांच्या
    1.34
     fornece
    1.34
     nonché
    1.33
     semplicemente
    1.33
     tuttavia
    1.32
     fornisce
    1.32
     fornire
    1.29
     करण्यासाठी
    1.29
     त्यांना
    1.28
    POSITIVE LOGITS
    ¿
    0.81
    ...
    0.77
    …
    0.69
     gastronomy
    0.68
    Ó
    0.62
    ..
    0.61
    ¡
    0.61
    \
    0.60
    ó
    0.59
     Já
    0.59
    Act Density 0.524%

    No Known Activations