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

    Neuronpedia

    INDEX
    Explanations

    SEO

    np_max-act · gemini-2.0-flash

    This neuron detects list‐style headings or “listicle” titles, especially ones beginning with “Top [number] …” followed by topic words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ола
    -0.08
    _request
    -0.07
    Some
    -0.07
    沈
    -0.07
    messages
    -0.07
    egade
    -0.06
    168
    -0.06
    appId
    -0.06
    �
    -0.06
    ro
    -0.06
    POSITIVE LOGITS
     makeshift
    0.07
     Глав
    0.06
     supplementary
    0.06
     Maher
    0.06
    MARY
    0.06
     Alleg
    0.05
    ;&#
    0.05
    �
    0.05
     nickname
    0.05
    中文
    0.05
    Act Density 0.059%

    No Known Activations