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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or events in a legal or formal context

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

    actions that had happened

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.54
    setVerticalGroup
    -0.51
     kicks
    -0.48
     nästa
    -0.48
     gets
    -0.47
     goes
    -0.47
     sienta
    -0.46
    исленность
    -0.46
    goes
    -0.46
     noDo
    -0.45
    POSITIVE LOGITS
     previously
    0.81
     zuvor
    0.71
     anteriormente
    0.70
    previously
    0.69
     auparavant
    0.68
     previamente
    0.67
     had
    0.65
     précédemment
    0.65
     Previously
    0.64
    Previously
    0.64
    Act Density 0.138%

    No Known Activations