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

    Neuronpedia

    INDEX
    Explanations

    address

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that indicate postal or street address fields (e.g. “Address,” “Endereço,” “Indirizzo”), i.e. address-related labels in forms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _ID
    -0.06
     txn
    -0.06
     ":"
    -0.06
    avg
    -0.06
    chart
    -0.06
     immersion
    -0.06
     آز
    -0.06
    fx
    -0.06
    aaaa
    -0.06
    Else
    -0.06
    POSITIVE LOGITS
     ADDRESS
    0.08
    /orders
    0.07
    letal
    0.07
    RenderTarget
    0.07
     GAL
    0.07
     `↵
    0.06
    .Q
    0.06
     بغ
    0.06
     flexDirection
    0.06
    二二二二
    0.06
    Act Density 0.014%

    No Known Activations