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

    Neuronpedia

    INDEX
    Explanations

    characters or events involving power struggles and threats

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

    following prepositions

    np_acts-logits-general · gemini-2.0-flash

    dragon, kingdoms, names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jefus
    -0.66
    verwijspagina
    -0.61
     Sopho
    -0.58
     Chriftian
    -0.57
    MLLoader
    -0.55
     gynhyrchwyd
    -0.54
     kasarigan
    -0.54
     Khrushchev
    -0.53
     Urugu
    -0.51
     transfieras
    -0.51
    POSITIVE LOGITS
     Dragon
    0.67
    Dragon
    0.64
    planar
    0.60
     dragon
    0.60
     dragons
    0.59
     Val
    0.57
    hael
    0.57
     dragón
    0.57
     kingdoms
    0.56
    大陆
    0.56
    Act Density 0.521%

    No Known Activations