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

    Neuronpedia

    INDEX
    Explanations

    inventions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SE
    0.38
    SOC
    0.37
    cmd
    0.35
    abul
    0.35
     overnight
    0.35
    aid
    0.34
    eared
    0.34
    SIN
    0.34
     ["[
    0.34
    зна
    0.34
    POSITIVE LOGITS
    ğmen
    0.43
     INVENTION
    0.42
     Dél
    0.42
    ඛ
    0.41
    產業
    0.40
    閒
    0.40
     ጣ
    0.40
     inventions
    0.39
     மேல்
    0.39
    り返
    0.39
    Act Density 0.000%

    No Known Activations