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

    Neuronpedia

    INDEX
    Explanations

    .tail

    np_max-act · gemini-2.0-flash

    Tokens at the start of an assistant-generated reply (the boundary/marker indicating a model/assistant response).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
    autos
    -0.07
     theoret
    -0.06
    인트
    -0.06
    prep
    -0.06
    first
    -0.06
    	Vector
    -0.06
    равиль
    -0.06
    (parcel
    -0.06
    .Framework
    -0.06
    Synopsis
    -0.06
    POSITIVE LOGITS
     ''}↵
    0.07
     Say
    0.06
     등
    0.06
    :"",↵
    0.06
     STYLE
    0.06
     situaci
    0.06
     significa
    0.06
    :'',↵
    0.06
     arguing
    0.06
    COVERY
    0.06
    Act Density 0.025%

    No Known Activations