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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash

    This neuron detects the special token marking the end of a user header segment (<|end_header_id|>).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    vised
    -0.07
     CCT
    -0.06
    693
    -0.06
     Pharmaceuticals
    -0.06
     丶
    -0.06
     程
    -0.06
    och
    -0.06
    .datasets
    -0.06
     Semiconductor
    -0.06
     nurture
    -0.05
    POSITIVE LOGITS
    dou
    0.07
                                   ↵
    0.06
    ()
    0.06
     gratuits
    0.06
     Tigers
    0.06
     Mortgage
    0.06
     proceed
    0.06
     Cyrus
    0.06
    CHIP
    0.06
     Benghazi
    0.06
    Act Density 0.016%

    No Known Activations