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

    Neuronpedia

    INDEX
    Explanations

    printing system output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sheet
    0.69
    त्सा
    0.65
    atron
    0.62
    atelli
    0.61
     scrolled
    0.61
     parted
    0.61
     disconnection
    0.60
     Hail
    0.58
     signOut
    0.58
     Chain
    0.58
    POSITIVE LOGITS
    __(
    0.77
    မ်း
    0.76
     केन्द्रीय
    0.75
    ₂(
    0.75
     유사
    0.74
     obserw
    0.74
     দিবার
    0.74
    (?:
    0.74
     কাজে
    0.73
    ordat
    0.73
    Act Density 0.002%

    No Known Activations