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

    Neuronpedia

    INDEX
    Explanations

    recommend

    np_max-act · gemini-2.0-flash

    The neuron activates on explicit customer endorsements and ratings—tokens like star counts and words such as “recommend” or “definitely.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     floating
    -0.06
     Address
    -0.06
    plets
    -0.06
    альное
    -0.06
    temperature
    -0.06
     address
    -0.06
    OCKET
    -0.06
     क
    -0.06
     Display
    -0.06
     persistent
    -0.06
    POSITIVE LOGITS
    ाध
    0.07
     Sở
    0.06
    popover
    0.06
    zeit
    0.06
     cada
    0.06
     hlavou
    0.06
    ':['
    0.06
     destinationViewController
    0.06
    facebook
    0.06
    VG
    0.06
    Act Density 0.010%

    No Known Activations