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

    Neuronpedia

    INDEX
    Explanations

    Plan

    np_max-act · gemini-2.0-flash

    discussions regarding planning and budgeting processes within municipalities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects mentions of formal planning documents by firing strongly on the word “Plan” (often with its preceding modifier) in titles or headings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
    itions
    -0.07
    -fed
    -0.06
    .Ph
    -0.06
    �
    -0.06
     jedoch
    -0.06
    Pol
    -0.06
    Validity
    -0.05
    _partition
    -0.05
     priority
    -0.05
    POSITIVE LOGITS
     普通
    0.07
     deviceId
    0.07
    /e
    0.07
    جة
    0.07
     Activate
    0.06
     krás
    0.06
    .deepEqual
    0.06
     Jens
    0.06
     Locke
    0.06
     cached
    0.06
    Act Density 0.023%

    No Known Activations