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

    Neuronpedia

    INDEX
    Explanations

    change into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ۽
    0.82
     và
    0.80
    的方式
    0.73
     及
    0.71
     consapevole
    0.71
     եւ
    0.71
     和
    0.69
    ওয়্যার
    0.68
    ആര്‍
    0.68
    ministrazione
    0.67
    POSITIVE LOGITS
     It
    0.85
    "
    0.84
    n
    0.80
    o
    0.79
    in
    0.73
    os
    0.73
    :
    0.73
    f
    0.72
    א
    0.70
    ق
    0.68
    Act Density 0.013%

    No Known Activations