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

    Neuronpedia

    INDEX
    Explanations

    value labels and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     windy
    0.62
     ಹೇಳಿದರು
    0.61
     univer
    0.59
     swoop
    0.55
    Bool
    0.54
     confuse
    0.54
     ዓይነ
    0.54
     ብዙውን
    0.54
    city
    0.54
     بخير
    0.54
    POSITIVE LOGITS
     of
    0.85
    ০
    0.70
     د
    0.69
    ación
    0.69
    د
    0.69
    ема
    0.66
    اء
    0.66
    ਾਬ
    0.66
    ش
    0.65
    е
    0.64
    Act Density 0.000%

    No Known Activations