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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    This neuron detects library or module path tokens (e.g. names in import/include file paths).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    WIN
    -0.07
    βο
    -0.07
     $("
    -0.06
     Rahman
    -0.06
    ]()
    -0.06
     北京
    -0.06
    держ
    -0.06
    Unlock
    -0.06
    Late
    -0.06
     Output
    -0.06
    POSITIVE LOGITS
    حيح
    0.08
    -collection
    0.07
     blessing
    0.07
     bulls
    0.07
     fecha
    0.06
     Crow
    0.06
    елей
    0.06
    AUSE
    0.06
    ٩
    0.06
     quang
    0.06
    Act Density 0.197%

    No Known Activations