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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the concept of "sometimes" or occurrences that suggest variability and subjectivity in experiences

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

    introduces observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.59
    WriteBarrier
    -0.56
    bootstrapcdn
    -0.55
    bindingNavigator
    -0.54
    TagMode
    -0.54
     pinulongan
    -0.53
    WebElementEntity
    -0.53
    rawDesc
    -0.50
    قایناق‌لار
    -0.50
     nakalista
    -0.49
    POSITIVE LOGITS
    enumi
    0.46
     you
    0.45
     člověk
    0.44
     we
    0.44
     things
    0.43
    คนที่
    0.43
     simplicité
    0.43
     simplicity
    0.41
     it
    0.41
     elämä
    0.41
    Act Density 0.011%

    No Known Activations