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

    Neuronpedia

    INDEX
    Explanations

    rates and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fractional
    0.66
     right
    0.62
     ab
    0.59
     Ab
    0.59
    iong
    0.58
     सिक्के
    0.57
    ہری
    0.57
    ifi
    0.57
     приветствую
    0.57
     ev
    0.56
    POSITIVE LOGITS
     главным
    0.72
     ट्रॉप
    0.70
     লিল
    0.68
    Sah
    0.68
     tih
    0.67
    اسى
    0.67
     тог
    0.66
    defer
    0.65
    гістра
    0.65
     செயல்
    0.65
    Act Density 0.001%

    No Known Activations