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

    Neuronpedia

    INDEX
    Explanations

    .D

    np_max-act · gemini-2.0-flash

    This neuron detects judicial‐district court abbreviations (like “E.D.N.C.” or “E.D.Va.”) in case citations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ino
    -0.07
    َي
    -0.07
    INO
    -0.07
    arsity
    -0.07
    ِن
    -0.07
    ala
    -0.07
    لمه
    -0.07
    uelle
    -0.07
    807
    -0.06
    \'
    -0.06
    POSITIVE LOGITS
    .attributes
    0.08
    aming
    0.07
     gió
    0.07
     Bordeaux
    0.06
     свобод
    0.06
    ,image
    0.06
     rubble
    0.06
     ภาษ
    0.06
    ніверсит
    0.06
     Nimbus
    0.06
    Act Density 0.001%

    No Known Activations