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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    state and city names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.42
    estacks
    -0.42
    sequ
    -0.42
    GetEnumerator
    -0.41
    DeleteBehavior
    -0.40
     epochs
    -0.38
     noDo
    -0.38
    RenderAtEndOf
    -0.38
    tadır
    -0.38
    ものである
    -0.37
    POSITIVE LOGITS
    APOLIS
    0.65
    ADELPHIA
    0.61
    WAUKEE
    0.60
    Calif
    0.57
     Calif
    0.56
    itoba
    0.55
    LANTA
    0.55
    })*/
    0.52
    Iowa
    0.52
     Iowa
    0.49
    Act Density 0.043%

    No Known Activations