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

    Neuronpedia

    INDEX
    Explanations

    programming constructs (loops, data types)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒂠
    0.53
    羥
    0.51
    𒋩
    0.50
     ইংরাজ
    0.50
    铒
    0.50
     পূর্ববাংলা
    0.50
    ሢ
    0.49
    薁
    0.49
     suppuration
    0.49
    砻
    0.48
    POSITIVE LOGITS
    ↵
    0.59
    i
    0.52
     (
    0.50
    0.50
    s
    0.50
    0
    0.49
     b
    0.49
    tr
    0.49
    a
    0.48
    c
    0.48
    Act Density 0.253%

    No Known Activations