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

    Neuronpedia

    INDEX
    Explanations

    chain emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wohnung
    -0.08
    สนาม
    -0.08
    simulation
    -0.08
     boutique
    -0.08
     monoxide
    -0.07
    ’agence
    -0.07
     ஈ
    -0.07
     Malo
    -0.07
     төҙ
    -0.07
    乙
    -0.07
    POSITIVE LOGITS
     forwarded
    0.09
     perlu
    0.08
     cultur
    0.08
     divisor
    0.08
     interessantes
    0.08
     diferenças
    0.08
     interesante
    0.08
     fibrosis
    0.07
     ursprünglich
    0.07
     sexist
    0.07
    Act Density 0.014%

    No Known Activations