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

    Neuronpedia

    INDEX
    Explanations

    technical/research texts

    np_max-act · gemini-2.0-flash

    The neuron responds to key content-bearing nouns and terms—highlighting topical or domain-specific keywords (like “use,” “awarded,” “run,” “MRI,” etc.) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ovich
    -0.07
     sales
    -0.06
     lender
    -0.06
     Printer
    -0.06
     minced
    -0.06
    	br
    -0.06
    <Q
    -0.06
     stabilize
    -0.06
     spills
    -0.06
    _ART
    -0.06
    POSITIVE LOGITS
     telefone
    0.07
     descricao
    0.07
    @Setter
    0.06
     miracles
    0.06
    licht
    0.06
     SharedModule
    0.06
    CreateTime
    0.06
    ορειο
    0.06
    ิ์
    0.06
    .CommandText
    0.06
    Act Density 0.252%

    No Known Activations