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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation or acknowledgment in various contexts

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

    introduces a specific statement or relationship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sauvages
    -0.60
     térmico
    -0.55
     transfieras
    -0.52
     aéreo
    -0.50
    MessageOf
    -0.49
     fédé
    -0.48
     $_"
    -0.47
     ffilmiau
    -0.47
     courseId
    -0.47
     desmotivaciones
    -0.46
    POSITIVE LOGITS
    LookAnd
    0.65
     newBuilder
    0.41
    endregion
    0.36
     ostavi
    0.35
    StartTag
    0.33
    NonUser
    0.33
     الاطلاع
    0.33
    IntentFilter
    0.33
    гән
    0.33
    chooser
    0.32
    Act Density 0.222%

    No Known Activations