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

    Neuronpedia

    INDEX
    Explanations

    the term "max" and its variations in different contexts related to limits or thresholds

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

    max as prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.71
     Pelle
    -0.45
    TRIBUT
    -0.45
    utter
    -0.43
    tring
    -0.41
     Scri
    -0.41
    iod
    -0.40
    ling
    -0.40
    ded
    -0.40
    the
    -0.39
    POSITIVE LOGITS
     Max
    1.17
    Max
    1.15
     max
    1.09
    max
    1.07
     MAX
    1.02
    getMax
    1.01
    MAX
    1.01
     getMax
    1.00
     Maxx
    0.90
    setMax
    0.89
    Act Density 0.026%

    No Known Activations