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

    Neuronpedia

    INDEX
    Explanations

    various documents/excerpts

    np_max-act · gemini-2.0-flash

    This neuron detects special control or markup tokens (e.g. “<|begin_of_text|>,” “<|start_header_id|>,” etc.) rather than natural-language words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _ci
    -0.07
     rue
    -0.07
    adients
    -0.07
     bmp
    -0.07
    _tags
    -0.07
    pe
    -0.06
     Blvd
    -0.06
    .Service
    -0.06
     Boulevard
    -0.06
    ẳng
    -0.06
    POSITIVE LOGITS
     está
    0.07
     Supporting
    0.07
     pode
    0.07
    。”
    0.06
     remains
    0.06
     Beard
    0.06
     "../../../
    0.06
     古
    0.06
     грудня
    0.06
     vivo
    0.06
    Act Density 0.000%

    No Known Activations