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

    Neuronpedia

    INDEX
    Explanations

    code-related text

    np_max-act · gemini-2.0-flash

    This neuron detects the special header‐ID markers (“<|start_header_id|>” and “<|end_header_id|>”) in the formatted chat transcript.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     já
    -0.07
    eştir
    -0.06
    Ju
    -0.06
    esidir
    -0.06
    licted
    -0.06
    UNET
    -0.06
    �
    -0.06
     purposes
    -0.06
    ést
    -0.06
    MDB
    -0.06
    POSITIVE LOGITS
     ether
    0.07
    ilio
    0.07
     compensated
    0.06
    IND
    0.06
     Edison
    0.06
     dei
    0.06
     personality
    0.06
     *((
    0.06
     icing
    0.06
     Villa
    0.06
    Act Density 0.046%

    No Known Activations