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

    Neuronpedia

    INDEX
    Explanations

    geocaching

    np_max-act · gemini-2.0-flash

    The neuron is triggered by geocaching–style treasure-hunt terms (e.g. cache, treasure, GPS coordinates, hunting, container).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (prom
    -0.07
     Tank
    -0.06
    _tunnel
    -0.06
    _bo
    -0.06
    (long
    -0.06
    ằm
    -0.06
    Paused
    -0.06
     JR
    -0.06
    .with
    -0.06
    unknown
    -0.06
    POSITIVE LOGITS
    звичай
    0.08
     nemovit
    0.07
    OutOfRangeException
    0.07
    iesel
    0.07
    viewController
    0.07
    esture
    0.06
     лишь
    0.06
     Opens
    0.06
    办
    0.06
    __((
    0.06
    Act Density 0.008%

    No Known Activations