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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act · gemini-2.0-flash

    Instances where the assistant gives a self-referential disclaimer describing itself as an AI language model and stating its capabilities/limitations.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
     Davidson
    -0.07
    xyz
    -0.07
    .master
    -0.06
     Memphis
    -0.06
     hol
    -0.06
     Mar
    -0.06
     Save
    -0.06
    mart
    -0.06
     Jo
    -0.06
    -example
    -0.06
    POSITIVE LOGITS
    sgi
    0.06
    hit
    0.06
     abilities
    0.06
    ]=]
    0.06
    ümüş
    0.06
    UPI
    0.06
     purch
    0.06
     ensure
    0.06
     未
    0.06
    otionEvent
    0.06
    Act Density 0.021%

    No Known Activations