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

    Neuronpedia

    INDEX
    Explanations

    desert

    np_max-act · gemini-2.0-flash

    The neuron is triggered by mentions of desert environments (e.g. the word “desert” and related context).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Registration
    -0.07
     Flush
    -0.07
     mnoha
    -0.07
     enqueue
    -0.07
     key
    -0.07
    -match
    -0.06
    нуться
    -0.06
    Order
    -0.06
     kulak
    -0.06
     shoes
    -0.06
    POSITIVE LOGITS
     desert
    0.14
     Desert
    0.12
     beach
    0.07
     Си
    0.06
    …
    0.06
     initialValue
    0.06
    (Http
    0.06
     appart
    0.06
    _ver
    0.06
    isseur
    0.06
    Act Density 0.005%

    No Known Activations