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

    Neuronpedia

    INDEX
    Explanations

    model answers

    np_acts-logits-general · gemini-2.5-flash-lite

    the token that marks the model/assistant’s turn in a chat transcript.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     ESM
    0.33
     пользователя
    0.33
    ्योर
    0.31
     रव
    0.31
     большой
    0.31
     úrov
    0.31
     большим
    0.30
    ﾛ
    0.30
    Cuánto
    0.30
    伡
    0.30
    POSITIVE LOGITS
    answer
    0.35
    Sources
    0.33
    Wikipedia
    0.33
     Sources
    0.31
     answer
    0.31
    sources
    0.31
    Answer
    0.30
    Mutual
    0.30
     Guinness
    0.29
    Sadly
    0.29
    Act Density 0.006%

    No Known Activations