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

    Neuronpedia

    INDEX
    Explanations

    sentence endings or pauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uh
    0.55
     (“
    0.49
     eighty
    0.48
     немно
    0.47
     (‘
    0.46
    ８
    0.43
     seventy
    0.42
     („
    0.42
    或者是
    0.41
     می‌باشد
    0.40
    POSITIVE LOGITS
     Are
    0.43
     Absolutely
    0.43
     Damn
    0.43
     Thankfully
    0.41
     Were
    0.41
     Tornado
    0.41
    ']
    0.40
     Due
    0.39
     Numerous
    0.39
    '],
    0.38
    Act Density 0.002%

    No Known Activations