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

    Neuronpedia

    INDEX
    Explanations

    technical/legal documents

    np_max-act · gemini-2.0-flash

    The neuron is triggered by the coordinating conjunction “and.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cavalry
    -0.07
     banda
    -0.06
     hinter
    -0.06
    535
    -0.06
     эконом
    -0.06
    grade
    -0.06
     {};↵
    -0.06
     ownerId
    -0.06
     فرو
    -0.06
    717
    -0.06
    POSITIVE LOGITS
     exemptions
    0.06
    Sync
    0.06
     gerek
    0.06
    ’den
    0.06
    Up
    0.06
    Sk
    0.06
    ařilo
    0.06
    UP
    0.06
    -driving
    0.06
    'nde
    0.06
    Act Density 0.686%

    No Known Activations