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

    Neuronpedia

    INDEX
    Explanations

    references to character actions and plot developments

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

    a lot, the themes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vôtre
    -0.43
    vité
    -0.41
    ंदीखरीदारी
    -0.39
    ambién
    -0.38
    courir
    -0.37
    ignty
    -0.36
     alér
    -0.35
     vän
    -0.35
     servers
    -0.35
    tiken
    -0.35
    POSITIVE LOGITS
    ついに
    0.52
    Vidite
    0.52
     implode
    0.49
     martyrdom
    0.48
    djangoproject
    0.47
     desperate
    0.45
     desperately
    0.45
    ParallelGroup
    0.44
    setof
    0.44
     imp
    0.44
    Act Density 0.019%

    No Known Activations