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

    Neuronpedia

    INDEX
    Explanations

    Trade

    np_max-act · gemini-2.0-flash

    The neuron responds to street‐address line tokens—particularly the leading house number and adjoining street name words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     �
    -0.07
    AT
    -0.06
    omap
    -0.06
    aths
    -0.06
    цять
    -0.06
    pie
    -0.06
    dın
    -0.06
    OVE
    -0.06
     SNMP
    -0.06
     başlay
    -0.06
    POSITIVE LOGITS
    uo
    0.07
     decrypt
    0.07
     ushort
    0.07
    �
    0.07
    Protected
    0.06
    攻
    0.06
    cido
    0.06
    greSQL
    0.06
    :self
    0.06
    -scalable
    0.06
    Act Density 0.003%

    No Known Activations