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

    Neuronpedia

    INDEX
    Explanations

    specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    1.15
     または
    1.07
    f
    1.05
    ہ
    1.04
    e
    1.02
    ה
    1.02
     Л
    1.01
    ian
    1.00
     ม
    1.00
     l
    0.98
    POSITIVE LOGITS
     desktops
    1.25
     ETFs
    1.16
    おります
    1.09
    ます
    1.08
     egiten
    1.07
     macarons
    1.05
     scones
    1.04
     supergiants
    1.03
     blockchains
    1.02
    ますが
    1.02
    Act Density 0.055%

    No Known Activations