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

    Neuronpedia

    INDEX
    Explanations

    foreign, borrowed, or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    low
    0.85
    root
    0.85
    US
    0.84
    UN
    0.75
    lywood
    0.75
    1
    0.74
    old
    0.74
    row
    0.74
    head
    0.74
    En
    0.74
    POSITIVE LOGITS
     verre
    1.50
     liberté
    1.39
     mécanique
    1.35
     chaque
    1.34
     della
    1.32
     chaude
    1.32
     tecnico
    1.31
     kulit
    1.29
     politique
    1.29
     Livre
    1.29
    Act Density 0.218%

    No Known Activations