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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the Python byte-code cache directory (tokens forming “__pycache__”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     detr
    -0.07
    atab
    -0.07
    $type
    -0.06
    приєм
    -0.06
     单
    -0.06
    SELL
    -0.06
    .real
    -0.06
     SST
    -0.06
    Few
    -0.06
    LineEdit
    -0.06
    POSITIVE LOGITS
     ΕΛ
    0.07
     Requests
    0.06
    ρας
    0.06
     required
    0.06
     reflex
    0.06
     musel
    0.06
     Thánh
    0.06
    encia
    0.06
    ồ
    0.06
     Render
    0.06
    Act Density 0.011%

    No Known Activations