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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    tokens marking conversation structure or speaker/header boundaries (special control tokens like start/end header, speaker IDs, or turn delimiters).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Βροχή
    -0.07
    キー
    -0.07
     съ
    -0.06
     weekdays
    -0.06
    Ｃ
    -0.06
    .AppSettings
    -0.06
    दम
    -0.06
    iyorlar
    -0.06
     �
    -0.06
    Resp
    -0.06
    POSITIVE LOGITS
    .n
    0.07
    _ask
    0.07
    =request
    0.07
     vertex
    0.07
     ruler
    0.06
     Gian
    0.06
     contest
    0.06
     Legislative
    0.06
    -coordinate
    0.06
    _fields
    0.06
    Act Density 0.072%

    No Known Activations