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

    Neuronpedia

    INDEX
    Explanations

    references to popular culture, particularly names and phrases associated with celebrities and entertainment

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

    Flamingo, Body Language, Gringo, Bummer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.42
     scelte
    -0.38
     maggiori
    -0.37
    ]];
    -0.35
    équilibre
    -0.34
     condizioni
    -0.34
     okol
    -0.34
    ))[
    -0.32
     aanbied
    -0.32
     strutture
    -0.31
    POSITIVE LOGITS
     pleaſure
    0.64
     hilarious
    0.62
     enfans
    0.60
    astify
    0.60
     Efq
    0.60
    ſelf
    0.59
     étoit
    0.58
     ſche
    0.58
     crazy
    0.56
    ⤹
    0.56
    Act Density 0.065%

    No Known Activations