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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference specific contexts or frameworks for discussions

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

    in terms of X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FieldBuilder
    -0.55
     оригіналу
    -0.46
    InjectAttribute
    -0.45
     AssemblyCulture
    -0.43
    addPreferredGap
    -0.43
     createSprite
    -0.42
     basket
    -0.41
     للاسماء
    -0.40
    compet
    -0.40
    栩
    -0.40
    POSITIVE LOGITS
     hinsichtlich
    0.74
    Regarding
    0.73
     bezüglich
    0.72
     regarding
    0.66
     Regarding
    0.65
    Concerning
    0.63
     privind
    0.61
     dotyczące
    0.60
     rispetto
    0.59
     щодо
    0.59
    Act Density 0.014%

    No Known Activations