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

    Neuronpedia

    INDEX
    Explanations

    references to maximum values or maximum limits in numeric contexts

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

    maximum values and related abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.62
    ppl
    -0.48
     doc
    -0.46
     shuffle
    -0.45
    DIT
    -0.45
     infile
    -0.44
    dud
    -0.44
    doin
    -0.44
     buckle
    -0.44
     FOL
    -0.43
    POSITIVE LOGITS
    max
    1.73
    MAX
    1.14
    Max
    0.97
    maxx
    0.82
    xmax
    0.81
    imax
    0.79
    マックス
    0.79
    setMax
    0.73
    getMax
    0.71
    ymax
    0.71
    Act Density 0.010%

    No Known Activations