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

    Neuronpedia

    INDEX
    Explanations

    Questions and responses

    np_max-act · gemini-2.0-flash

    Looks for special control/header tokens and conversation boundary markers (e.g., start/end/eot and speaker-header tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    Road
    -0.08
     Hazard
    -0.07
    addGroup
    -0.07
    paste
    -0.06
     Christmas
    -0.06
     prev
    -0.06
    �
    -0.06
     дерев
    -0.06
     TE
    -0.06
     us
    -0.06
    POSITIVE LOGITS
    .CreateInstance
    0.06
    '];↵
    0.06
     ww
    0.06
     amazon
    0.06
    iffies
    0.06
     اجازه
    0.06
    "><?
    0.06
    -wsj
    0.06
    ,proto
    0.06
    RuntimeException
    0.06
    Act Density 0.082%

    No Known Activations