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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    code and functionality related to API development and authentication mechanisms.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    orget
    -0.07
    ิต
    -0.07
     medals
    -0.07
     Leonard
    -0.07
    Practice
    -0.06
     inference
    -0.06
    actus
    -0.06
    Recording
    -0.06
    _quit
    -0.06
    http
    -0.06
    POSITIVE LOGITS
    isz
    0.06
    reds
    0.06
    toLocale
    0.06
    :pointer
    0.06
    avigation
    0.06
     insecure
    0.06
    ahoo
    0.06
    noDB
    0.06
    .hidden
    0.06
     стад
    0.06
    Act Density 0.023%

    No Known Activations