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

    Neuronpedia

    INDEX
    Explanations

    Japanese and Korean characters indicating years and dates

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

    years and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    interface
    -0.41
    draw
    -0.40
    clearfix
    -0.39
    dsp
    -0.36
    box
    -0.36
     interface
    -0.35
    gib
    -0.34
    inside
    -0.33
    <bos>
    -0.33
     khỏi
    -0.33
    POSITIVE LOGITS
    年
    2.11
    년
    1.48
     年
    1.35
     year
    1.13
     년
    1.12
     YEAR
    1.09
     année
    1.09
    Year
    1.06
     Year
    1.05
    YEAR
    1.03
    Act Density 0.002%

    No Known Activations