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

    Neuronpedia

    INDEX
    Explanations

    references to control samples and their characteristics in scientific data

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

    control or model variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MessageBoxIcon
    -0.54
    expandindo
    -0.50
    IBOutlet
    -0.47
    ollectionView
    -0.44
     Normdatei
    -0.44
    HasAnnotation
    -0.44
    awtextra
    -0.44
    GEBURTSDATUM
    -0.43
     Numerade
    -0.42
    RemoteException
    -0.41
    POSITIVE LOGITS
    MigrationBuilder
    0.56
     itinéraires
    0.43
    Referanser
    0.39
     Heere
    0.38
     thiệu
    0.38
    冠
    0.37
     hech
    0.37
    出版年
    0.36
    曖昧さ回避
    0.36
     tiêu
    0.35
    Act Density 0.783%

    No Known Activations