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

    Neuronpedia

    INDEX
    Explanations

    history of non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.50
    izer
    0.49
    tax
    0.49
    ress
    0.47
    at
    0.46
    ेशनल
    0.45
    ẹp
    0.42
    in
    0.41
     IRS
    0.41
    ized
    0.41
    POSITIVE LOGITS
     glycoprotein
    0.51
     medici
    0.51
     Gletscher
    0.50
     concetto
    0.50
     facteur
    0.49
     squiggle
    0.48
     piatti
    0.47
     scienza
    0.47
     scienze
    0.47
     livres
    0.47
    Act Density 0.010%

    No Known Activations