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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "feature" and its variations in the context of media or content highlight

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

    featured on or in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Trennung
    -0.46
     cantora
    -0.45
     lentement
    -0.43
     européennes
    -0.40
     sèche
    -0.40
     kağıdı
    -0.40
     olup
    -0.40
    lioz
    -0.40
     falsche
    -0.39
     Schritte
    -0.38
    POSITIVE LOGITS
     feature
    1.30
     featured
    1.27
     Feature
    1.21
    feature
    1.18
     FEATURE
    1.15
     Featured
    1.13
    featured
    1.13
     features
    1.12
     featuring
    1.10
    Featured
    1.09
    Act Density 0.023%

    No Known Activations