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

    Neuronpedia

    INDEX
    Explanations

    code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    1.01
    3
    0.89
    Tuesday
    0.73
     Tues
    0.68
     Tuesday
    0.68
     ২৩
    0.67
     Dienstag
    0.66
     three
    0.63
    accep
    0.59
     mob
    0.58
    POSITIVE LOGITS
    ض
    0.80
    CONTENT
    0.79
    От
    0.79
     от
    0.76
     со
    0.76
    ༨
    0.76
    Съ
    0.76
     е
    0.75
     От
    0.73
     অ্যান্ট
    0.73
    Act Density 0.223%

    No Known Activations