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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    setViewportView
    -0.67
    <eos>
    -0.53
    burg
    -0.51
    }`}>
    -0.50
    vacy
    -0.48
     архивлан
    -0.48
    )?.
    -0.47
    AndEndTag
    -0.46
    ILayout
    -0.45
     pending
    -0.45
    POSITIVE LOGITS
     kasarigan
    0.70
    GEBURTSDATUM
    0.64
     écoles
    0.60
     enfans
    0.60
    Lähteet
    0.60
     beroep
    0.59
    Хьажоргаш
    0.57
     gesprek
    0.57
     sœurs
    0.56
     surla
    0.56
    Act Density 0.002%

    No Known Activations