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

    Neuronpedia

    INDEX
    Explanations

    list of programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.52
     Support
    0.42
     Figure
    0.41
     सपोर्ट
    0.39
     Marquette
    0.39
    ↵
    0.38
     Clean
    0.38
     Оба
    0.38
     nightclub
    0.37
     Sandia
    0.37
    POSITIVE LOGITS
    கடந்த
    0.38
    شتغل
    0.37
    ಂದು
    0.35
    డ్డి
    0.35
     druk
    0.34
    我们也
    0.34
    myfaces
    0.33
    बरी
    0.33
    改良
    0.33
     från
    0.33
    Act Density 0.000%

    No Known Activations