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

    Neuronpedia

    INDEX
    Explanations

    numerical comparisons and ratios

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

    than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.68
    featureID
    -0.65
    ImageContext
    -0.57
    kháu
    -0.56
    RegistryLite
    -0.54
     lenker
    -0.54
    QMetaType
    -0.53
    bitField
    -0.53
    dard
    -0.50
    CloseOperation
    -0.50
    POSITIVE LOGITS
     than
    0.54
    보다
    0.54
    よりも
    0.47
    よりは
    0.46
    than
    0.43
     worse
    0.42
     better
    0.41
     Than
    0.41
     より
    0.40
     decât
    0.39
    Act Density 0.105%

    No Known Activations