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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performance metrics or measurements

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

    performance of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.47
    MLLoader
    -0.44
     retraction
    -0.43
     <=",
    -0.43
     subtlety
    -0.43
     lacking
    -0.40
    Према
    -0.39
    ığın
    -0.37
     vielä
    -0.37
    httphttps
    -0.37
    POSITIVE LOGITS
    MigrationBuilder
    0.51
    awakeFromNib
    0.45
    AccessFile
    0.45
    featureID
    0.43
    :✨
    0.42
    ⤹
    0.40
     viewDidLoad
    0.40
     مشين
    0.39
    Попис
    0.39
    améli
    0.39
    Act Density 0.071%

    No Known Activations