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

    Neuronpedia

    INDEX
    Explanations

    brand names, specific names, quoted terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دان
    0.82
    TER
    0.79
    OG
    0.71
    Т
    0.67
    ilem
    0.65
    О
    0.64
    CCESS
    0.64
     (__
    0.63
    란
    0.63
    .}~\
    0.62
    POSITIVE LOGITS
    ද්ග
    0.79
     sushi
    0.79
     Espresso
    0.77
     engen
    0.77
    तेल
    0.76
     soda
    0.75
     Sauvignon
    0.75
     centrifugal
    0.75
     Malaria
    0.75
     Sulfur
    0.74
    Act Density 0.000%

    No Known Activations