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

    Neuronpedia

    INDEX
    Explanations

    elements related to popular culture and storytelling

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

    comparisons using "like"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     péri
    -0.35
    <bos>
    -0.30
     shape
    -0.30
    RefNanny
    -0.29
     contextes
    -0.28
     artikkelen
    -0.27
    shaped
    -0.27
    }){
    -0.27
    shape
    -0.26
     península
    -0.26
    POSITIVE LOGITS
    RegressionTest
    0.67
    ьаж
    0.66
    OrNil
    0.64
     FetchType
    0.64
     EconPapers
    0.62
     незавершена
    0.60
    انيف
    0.60
    expandindo
    0.59
    rungsseite
    0.58
    afficheront
    0.58
    Act Density 0.057%

    No Known Activations