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

    Neuronpedia

    INDEX
    Explanations

    instances of authorship or attribution in texts

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

    by [proper noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.64
    Personendaten
    -0.59
    Бахар
    -0.59
     ModelExpression
    -0.57
    Portail
    -0.55
    OGND
    -0.50
    出版年
    -0.48
     HasFactory
    -0.47
    -0.46
     CreateTagHelper
    -0.45
    POSITIVE LOGITS
    iyaki
    0.42
     diha
    0.40
     Ambiental
    0.36
    sno
    0.36
    enumi
    0.36
    nah
    0.35
     tratt
    0.35
     Residences
    0.35
    snapshots
    0.35
     Troy
    0.35
    Act Density 0.066%

    No Known Activations