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

    Neuronpedia

    INDEX
    Explanations

    objective

    np_max-act · gemini-2.0-flash

    mathematical models for optimization problems.

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

    This neuron activates on mentions of “objective function” (or similar phrases) in optimization contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    answer
    -0.06
    จร
    -0.06
    aussian
    -0.06
    Wal
    -0.06
    /resource
    -0.06
    ijkstra
    -0.06
    .flash
    -0.06
    ンテ
    -0.06
     heute
    -0.06
    !'↵
    -0.05
    POSITIVE LOGITS
    org
    0.08
     Mirage
    0.07
     void
    0.07
     truly
    0.07
     LLC
    0.06
     Adapter
    0.06
     três
    0.06
    -project
    0.06
    .Output
    0.06
    -lib
    0.06
    Act Density 0.006%

    No Known Activations