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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the verb “know,” especially when it’s used to open a user’s question (e.g. “Do you know…?”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     radar
    -0.07
     {!!
    -0.06
    (details
    -0.06
     bedding
    -0.06
     Women
    -0.06
    bases
    -0.05
    =file
    -0.05
     pager
    -0.05
     heatmap
    -0.05
    “That
    -0.05
    POSITIVE LOGITS
    aporation
    0.07
     sebeb
    0.07
    िज
    0.07
    STE
    0.07
     renew
    0.06
    rippling
    0.06
     remarkably
    0.06
     UIG
    0.06
    etermin
    0.06
     HOR
    0.06
    Act Density 0.017%

    No Known Activations