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

    Neuronpedia

    INDEX
    Explanations

    how do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polynom
    0.45
    |$,
    0.43
     exists
    0.42
     অস্তিত্ব
    0.42
    的美
    0.41
     бір
    0.40
    都在
    0.40
     futbol
    0.40
     dictators
    0.40
     stoichi
    0.39
    POSITIVE LOGITS
     Answer
    0.63
    Answer
    0.60
    According
    0.60
    The
    0.59
     The
    0.57
     Therefore
    0.57
     Introduction
    0.56
    Using
    0.55
    Dear
    0.54
    Therefore
    0.54
    Act Density 0.004%

    No Known Activations