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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act · gemini-2.0-flash

    mentions of LLM/LM/AI model identifiers or runtime-related tokens (references to language-model labels and runtime names).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    stories
    -0.07
     Cd
    -0.06
    directive
    -0.06
     horrifying
    -0.06
     Js
    -0.06
     UP
    -0.06
     WaitForSeconds
    -0.06
     DEA
    -0.06
    .registration
    -0.06
    -0.06
    POSITIVE LOGITS
     спад
    0.08
     слив
    0.07
     Advanced
    0.07
    关键
    0.06
     Verfüg
    0.06
    UIAlertAction
    0.06
    istles
    0.06
     Advances
    0.06
     Highly
    0.06
     επισ
    0.06
    Act Density 0.061%

    No Known Activations