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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making or significant events

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

    something happened after a delay

    np_acts-logits-general · gemini-2.0-flash

    final outcome or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immediately
    -1.10
    immediately
    -1.09
    Immediately
    -1.02
     Immediately
    -1.02
     immédiatement
    -0.97
     inmediatamente
    -0.96
     immediate
    -0.95
     instantly
    -0.90
     quickly
    -0.87
     Immediate
    -0.86
    POSITIVE LOGITS
     finally
    0.76
    finally
    0.68
     realization
    0.68
    ようやく
    0.66
     Finally
    0.66
     realisation
    0.65
    Finally
    0.65
    findpost
    0.64
     reach
    0.64
     enfin
    0.63
    Act Density 0.386%

    No Known Activations