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

    Neuronpedia

    INDEX
    Explanations

    references to characters and relationships in narratives

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

    he/she/it actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.35
     prati
    -0.31
     Moose
    -0.29
     tags
    -0.28
     purity
    -0.28
     diagon
    -0.28
    લી
    -0.28
    eventType
    -0.28
    AddTagHelper
    -0.28
     Gin
    -0.28
    POSITIVE LOGITS
     autorytatywna
    0.71
    PerformLayout
    0.64
    verifyException
    0.64
    Diweddarwch
    0.63
     الرياضيه
    0.62
    contentLoaded
    0.60
    aarrggbb
    0.57
    AutoField
    0.56
    GEBURTSDATUM
    0.55
     nakalista
    0.49
    Act Density 0.043%

    No Known Activations