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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron activates on C++ template parameter angle‐bracketed type names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     writer
    -0.07
    .git
    -0.07
    �
    -0.06
    军
    -0.06
    ighted
    -0.06
    れて
    -0.06
     بوده
    -0.06
    xBA
    -0.06
    essen
    -0.06
     narratives
    -0.06
    POSITIVE LOGITS
    'ye
    0.06
     Ан
    0.06
     üye
    0.06
    بالإنجليزية
    0.06
     Guam
    0.06
     Garage
    0.06
    最終
    0.06
    ۹
    0.06
    麻
    0.06
     quaint
    0.06
    Act Density 0.006%

    No Known Activations