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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or groups in a research context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Word following "only"

    np_acts-logits-general · gemini-2.0-flash

    only [entity]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.79
    sizeCache
    -0.76
    tvguidetime
    -0.75
     soon
    -0.75
    Xna
    -0.74
     just
    -0.73
     especially
    -0.69
     springfox
    -0.69
    Especially
    -0.68
     snart
    -0.67
    POSITIVE LOGITS
     ever
    0.80
     réellement
    0.72
     thôi
    0.71
     véritable
    0.71
    而已
    0.71
     remaining
    0.66
    才会
    0.65
     realmente
    0.64
     anymore
    0.63
     wirklich
    0.62
    Act Density 0.407%

    No Known Activations