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

    Neuronpedia

    INDEX
    Explanations

    characters' names and their dialogue in interactions

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

    nobleman and ancient Roman history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Reſ
    -0.84
    ſelf
    -0.84
     Majefty
    -0.83
     myſelf
    -0.81
     Efq
    -0.81
     itſelf
    -0.81
    ſelves
    -0.78
     Anſ
    -0.77
     ſte
    -0.73
     Eſ
    -0.73
    POSITIVE LOGITS
     ancient
    0.73
    Ancient
    0.69
    ancient
    0.68
     romanos
    0.66
     Ancient
    0.65
     griego
    0.63
     древ
    0.63
     grecque
    0.61
     sandalias
    0.60
     Roman
    0.59
    Act Density 0.220%

    No Known Activations