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

    Neuronpedia

    INDEX
    Explanations

    names that start with "Ra"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gir
    -0.68
    ners
    -0.63
     Imp
    -0.63
    5
    -0.63
    alan
    -0.62
     Bren
    -0.62
    Gir
    -0.62
     Bot
    -0.60
     آم
    -0.60
     Gour
    -0.60
    POSITIVE LOGITS
     Raim
    1.38
    Ra
    1.25
     RAID
    1.23
     Ra
    1.20
     Raider
    1.19
     RA
    1.18
     raisins
    1.18
     Raub
    1.13
     raider
    1.13
     Raoul
    1.11
    Act Density 0.025%

    No Known Activations