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

    Neuronpedia

    INDEX
    Explanations

    personal narratives

    np_max-act · gemini-2.0-flash

    Phrases where the speaker refers to themselves or their group (first-person pronouns like I/we/me) often with verbs expressing action or intent.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    מת
    -0.07
    _unknown
    -0.07
     Downs
    -0.07
     plataforma
    -0.07
    סופר
    -0.07
    航空公司
    -0.07
     arrange
    -0.07
     обо
    -0.06
     hypo
    -0.06
    몯
    -0.06
    POSITIVE LOGITS
    ∫
    0.08
     vm
    0.07
    (grid
    0.07
     Vers
    0.07
    ITIONS
    0.07
     Transactions
    0.07
    其它问题
    0.07
    特邀
    0.06
    ef
    0.06
    tc
    0.06
    Act Density 0.309%

    No Known Activations