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

    Neuronpedia

    INDEX
    Explanations

    .S

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the abbreviation “U.S” (as in statutory or case citations referencing the United States).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    fat
    -0.07
    Prot
    -0.07
    libraries
    -0.07
    SCRI
    -0.06
    پر
    -0.06
    erap
    -0.06
    ambiguous
    -0.06
    jay
    -0.06
    INTR
    -0.06
    (dtype
    -0.06
    POSITIVE LOGITS
     RootState
    0.07
    剩
    0.07
     moy
    0.06
     Email
    0.06
     Workout
    0.06
     encore
    0.06
    disposing
    0.06
    生成
    0.06
    руг
    0.06
    //************************************************************************
    0.06
    Act Density 0.002%

    No Known Activations