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

    Neuronpedia

    INDEX
    Explanations

    wine and food pairing

    np_acts-logits-general · gemini-2.5-flash-lite

    code structure elements and formatting in programming files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    路线
    -0.79
     soft
    -0.73
     earthquake
    -0.71
    LiveData
    -0.69
    weed
    -0.69
     early
    -0.68
     Soft
    -0.68
    挡
    -0.66
     toolbox
    -0.66
     Shopping
    -0.65
    POSITIVE LOGITS
     轮
    0.69
     Champlain
    0.65
     recuperar
    0.63
     Aik
    0.62
     Blueprint
    0.62
     класс
    0.62
     將
    0.60
    ீ
    0.60
    indle
    0.60
     comedor
    0.60
    Act Density 0.062%

    No Known Activations