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

    Neuronpedia

    INDEX
    Explanations

    reading comprehension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Excuse
    0.42
     pard
    0.41
     Feder
    0.39
    ru
    0.37
     excuse
    0.37
     정도
    0.37
     ș
    0.37
     agré
    0.37
     pardon
    0.37
     בח
    0.36
    POSITIVE LOGITS
     recipes
    0.46
     especies
    0.46
     chemicals
    0.46
    CrossRef
    0.45
    Diethyl
    0.45
    benzene
    0.45
    Dental
    0.44
     methods
    0.44
     angezeigt
    0.44
     দ্রব
    0.43
    Act Density 0.001%

    No Known Activations