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

    Neuronpedia

    INDEX
    Explanations

    Learning and doing

    np_max-act · gemini-2.0-flash

    This neuron activates on special header-boundary tokens (e.g. the `<|start_header_id|>` marker).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     LABEL
    -0.06
     prima
    -0.06
    Label
    -0.06
     d
    -0.06
     erv
    -0.06
     Opr
    -0.06
     POLITICO
    -0.06
    Metro
    -0.06
     Suzanne
    -0.06
    MenuItem
    -0.06
    POSITIVE LOGITS
    chten
    0.07
    -radius
    0.07
    وند
    0.07
     �
    0.06
    'nun
    0.06
    itti
    0.06
    -widgets
    0.06
     Votes
    0.06
    miner
    0.06
    .sax
    0.06
    Act Density 0.049%

    No Known Activations