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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act · gemini-2.0-flash

    the assistant claiming it was developed by Meta AI (developer attribution statements).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
    čast
    -0.07
    піон
    -0.06
     продукції
    -0.06
    ям
    -0.06
     pře
    -0.06
     अलग
    -0.06
    頓
    -0.06
     �
    -0.06
    сті
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ;;↵↵
    0.07
     BYU
    0.07
     excellence
    0.06
     enquiry
    0.06
     decency
    0.06
     philosoph
    0.06
     elect
    0.06
     next
    0.06
     martin
    0.06
    LOT
    0.06
    Act Density 0.000%

    No Known Activations