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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash

    connections between lobbying activities and political influence.

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

    This neuron activates on numeric sequences—particularly the decimal numbers in in-text citation codes or reference identifiers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Patton
    -0.07
    kraine
    -0.07
    üyük
    -0.07
    Serial
    -0.06
     ddl
    -0.06
    .chars
    -0.06
    Deaths
    -0.06
    617
    -0.06
     Mood
    -0.06
    นคร
    -0.06
    POSITIVE LOGITS
     tpl
    0.07
     Совет
    0.06
     rendition
    0.06
     ödül
    0.06
    cej
    0.06
    preload
    0.06
    茶
    0.06
    jes
    0.06
     restrained
    0.06
     characterize
    0.06
    Act Density 0.027%

    No Known Activations