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

    Neuronpedia

    INDEX
    Explanations

    Locations and information

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens in call-to-action or reader-instructions segments—phrases like “for more information,” “to view the menu,” “make reservations,” “visit…,” “register,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    daemon
    -0.07
    πλα
    -0.06
    	mp
    -0.06
    ливості
    -0.06
    .WebServlet
    -0.06
    aber
    -0.06
    ybrid
    -0.06
    POR
    -0.06
    lém
    -0.06
    /native
    -0.06
    POSITIVE LOGITS
    Bloc
    0.07
     unt
    0.06
     dissent
    0.06
     vay
    0.06
     >
    0.06
     dicho
    0.06
     revelation
    0.06
     pac
    0.06
     bì
    0.06
     Appe
    0.06
    Act Density 0.036%

    No Known Activations