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

    Neuronpedia

    INDEX
    Explanations

    programming concepts related to options and parameters, particularly those involving ignore or filter settings

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

    `keep` or `ignore` configurations

    np_acts-logits-general · gemini-2.0-flash

    ignore and keep flags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.49
      
    -0.41
     вами
    -0.41
    ,
    -0.41
     a
    -0.39
    的一个
    -0.38
    springframework
    -0.38
     there
    -0.37
     seseorang
    -0.37
     -
    -0.37
    POSITIVE LOGITS
    IntoConstraints
    1.33
     SafeMath
    1.01
     disambiguazione
    1.00
     ivelany
    0.94
    rungsseite
    0.92
    tvguidetime
    0.91
     betweenstory
    0.89
     propOrder
    0.89
     تضيفلها
    0.88
    Rüyada
    0.86
    Act Density 0.331%

    No Known Activations