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

    Neuronpedia

    INDEX
    Explanations

    00

    np_max-act · gemini-2.0-flash

    This neuron activates on backslash-u Unicode escape sequences (e.g. “\u00e9”) in code strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Productos
    -0.07
    ARS
    -0.07
     ASC
    -0.06
    Channel
    -0.06
     hatred
    -0.06
    gresql
    -0.06
     philosophy
    -0.06
     Masters
    -0.06
     programs
    -0.06
    ponsive
    -0.06
    POSITIVE LOGITS
    acaktır
    0.09
     biraz
    0.08
    ElementType
    0.07
    _ASSERT
    0.07
     такий
    0.07
    [jj
    0.07
    00
    0.07
     خیلی
    0.07
    fastcall
    0.07
    	EIF
    0.07
    Act Density 0.002%

    No Known Activations