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

    Neuronpedia

    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash

    statements about performance metrics and game outcomes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Fac
    -0.07
     Esper
    -0.07
    리즈
    -0.06
     Stopwatch
    -0.06
     epoll
    -0.06
    [G
    -0.06
     Š
    -0.06
    пе
    -0.06
    -Americ
    -0.06
    extended
    -0.06
    POSITIVE LOGITS
    asted
    0.07
    .TYPE
    0.07
     secretion
    0.07
     gelen
    0.06
    вати
    0.06
     stiffness
    0.06
     drawer
    0.06
     draws
    0.06
    存
    0.06
    (),
↵
    0.06
    Act Density 0.024%

    No Known Activations