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

    Neuronpedia

    INDEX
    Explanations

    file names with numbers and extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nuovo
    0.65
     habla
    0.64
    ان
    0.63
     mulai
    0.63
     மாதிர
    0.60
     yıl
    0.59
     beragam
    0.58
    ก
    0.57
     mendapat
    0.57
    szyst
    0.57
    POSITIVE LOGITS
     Californie
    0.65
    6
    0.62
     Geophysical
    0.62
    kirche
    0.61
     .
    0.61
    ews
    0.61
     Consulte
    0.61
    es
    0.60
    Се
    0.59
    7
    0.59
    Act Density 0.049%

    No Known Activations