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

    Neuronpedia

    INDEX
    Explanations

    Requirement to do something

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of government agencies, departments, and official bodies.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     decades
    -0.08
    Download
    -0.07
    itous
    -0.07
     Jet
    -0.07
    есть
    -0.07
    (bb
    -0.07
    onse
    -0.07
    Ⅵ
    -0.06
     konusu
    -0.06
    ACCESS
    -0.06
    POSITIVE LOGITS
     immutable
    0.07
    strpos
    0.06
     communion
    0.06
     })();↵
    0.06
     �
    0.06
     Alphabet
    0.06
     entend
    0.06
    catalog
    0.06
    fections
    0.06
     strang
    0.06
    Act Density 0.013%

    No Known Activations