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

    Neuronpedia

    INDEX
    Explanations

    might want to suggest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ett
    0.57
    ant
    0.56
    ettle
    0.56
    Maintaining
    0.55
     modell
    0.54
    AP
    0.51
    irstyle
    0.50
    ட்சிய
    0.49
    ANT
    0.48
    IT
    0.48
    POSITIVE LOGITS
    ൂ
    0.65
    x
    0.64
    رة
    0.62
    ти
    0.60
    スタン
    0.60
    בו
    0.59
     সাপ্তাহ
    0.59
    folds
    0.59
    عي
    0.59
     emphasized
    0.59
    Act Density 0.002%

    No Known Activations