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

    Neuronpedia

    INDEX
    Explanations

    typeof

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iteleri
    -0.07
     ایران
    -0.07
     caffeine
    -0.07
    아
    -0.06
     dzieci
    -0.06
    aniu
    -0.06
    itler
    -0.06
    ('/')
    -0.06
    (DEFAULT
    -0.06
     kní
    -0.06
    POSITIVE LOGITS
     arising
    0.07
    joining
    0.07
     observe
    0.07
     qw
    0.07
     allowable
    0.07
     typedef
    0.07
    =sys
    0.07
     wishing
    0.07
     Article
    0.07
    ';↵↵↵↵
    0.06
    Act Density 0.002%

    No Known Activations