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

    Neuronpedia

    INDEX
    Explanations

    references to newness or novelty

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

    new or novel things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pavillon
    -0.37
     voisin
    -0.35
    InSection
    -0.33
     Kasih
    -0.32
     indépendant
    -0.32
     hvě
    -0.31
     Administrativna
    -0.30
     despacho
    -0.30
     apparence
    -0.30
     assise
    -0.29
    POSITIVE LOGITS
     '\\;'
    0.68
    tagHelperRunner
    0.64
    Portail
    0.61
    ErrUnexpectedEOF
    0.60
     Audiodateien
    0.59
    twimg
    0.58
    oluble
    0.55
     disambiguazione
    0.55
     BaseEntity
    0.50
    ########.
    0.50
    Act Density 0.005%

    No Known Activations