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

    Neuronpedia

    INDEX
    Explanations

    assertions of truth or certainty, particularly concerning facts and their verification

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

    in fact or indeed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.48
     Knud
    -0.45
    subcategory
    -0.44
     Reſ
    -0.43
     instin
    -0.42
     mous
    -0.42
    wiſe
    -0.42
     Inſ
    -0.42
     Perſ
    -0.41
     overla
    -0.41
    POSITIVE LOGITS
     indeed
    0.83
     inderdaad
    0.78
     appunto
    0.76
    Personendaten
    0.73
    indeed
    0.71
     tatsächlich
    0.70
    Indeed
    0.69
     effectivement
    0.68
     kaarangay
    0.66
     Indeed
    0.65
    Act Density 0.013%

    No Known Activations