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

    Neuronpedia

    INDEX
    Explanations

    graph edges and vertices

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “edges’ names,” i.e. references to the names or labels of edges.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Rejected
    -0.06
    )').
    -0.06
    (Entity
    -0.06
     eventData
    -0.06
     Execution
    -0.06
     olmadı
    -0.06
    importDefault
    -0.06
     Italia
    -0.06
     Norfolk
    -0.06
     kỹ
    -0.06
    POSITIVE LOGITS
     USB
    0.07
    贝
    0.07
    기에
    0.06
    .minimum
    0.06
     nombreux
    0.06
     snakes
    0.06
     와
    0.06
    ैट
    0.06
     gerç
    0.06
     reversal
    0.06
    Act Density 0.038%

    No Known Activations