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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating transitions or changes in states

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

    ending in "in," "an," or "on."

    np_acts-logits-general · gemini-2.0-flash

    parts of names and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     special
    -0.54
    skal
    -0.43
    </tr>
    -0.43
    nings
    -0.42
     roll
    -0.42
     H
    -0.42
     proceed
    -0.41
    kos
    -0.41
    ROLL
    -0.41
    roll
    -0.41
    POSITIVE LOGITS
     AssemblyCulture
    0.96
     propOrder
    0.84
     nakalista
    0.80
    astéroïdes
    0.78
    Біографія
    0.77
     avoient
    0.76
    webElementXpaths
    0.75
    RenderAtEndOf
    0.74
     säll
    0.74
     lenker
    0.73
    Act Density 0.150%

    No Known Activations