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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron identifies the “Day N:” headings in multi‐day travel itineraries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Excell
    -0.07
     خل
    -0.07
     paren
    -0.07
     OA
    -0.07
     hashmap
    -0.07
     protests
    -0.07
     pe
    -0.07
     findBy
    -0.07
     headed
    -0.06
     Correction
    -0.06
    POSITIVE LOGITS
    -v
    0.07
     który
    0.07
    793
    0.06
    gw
    0.06
    .Resource
    0.06
    лаг
    0.06
    .bmp
    0.06
     والإ
    0.06
    něm
    0.06
    482
    0.06
    Act Density 0.014%

    No Known Activations