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

    Neuronpedia

    INDEX
    Explanations

    Technical/Code documents

    np_max-act · gemini-2.0-flash

    The neuron is looking for mentions of sorting or ordering operations (e.g. “sorted,” “ORDER BY,” “in alphabetical order,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     CPF
    -0.07
     фас
    -0.07
     =====
    -0.07
    dotenv
    -0.06
     Camb
    -0.06
    cases
    -0.06
    .topAnchor
    -0.06
     κατά
    -0.06
    =A
    -0.06
     mav
    -0.06
    POSITIVE LOGITS
     ap
    0.06
     своих
    0.06
     Bert
    0.06
     milyon
    0.06
     Gain
    0.06
    /version
    0.06
     vest
    0.05
     istiyor
    0.05
    iydi
    0.05
    ponsored
    0.05
    Act Density 0.394%

    No Known Activations