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

    Neuronpedia

    INDEX
    Explanations

    money and spirit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     calculators
    0.40
     resTmp
    0.38
     لمدة
    0.34
    数学
    0.34
    數學
    0.34
    プログラム
    0.34
     (!)
    0.33
    (!)
    0.33
     계산
    0.33
    !">
    0.33
    POSITIVE LOGITS
     ol
    0.44
    finaly
    0.44
    ydı
    0.42
    Show
    0.42
    ху
    0.41
     tru
    0.41
    inken
    0.41
    𝚑
    0.41
     _,
    0.40
     earliest
    0.40
    Act Density 0.008%

    No Known Activations