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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash

    This neuron detects the special “<|end_header_id|>” token that marks the end of a header block.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    accion
    -0.06
    apper
    -0.06
    oka
    -0.06
    uction
    -0.06
     ":"
    -0.06
     upd
    -0.06
     villains
    -0.06
     Bend
    -0.06
     نوشته
    -0.06
    층
    -0.06
    POSITIVE LOGITS
    地區
    0.07
     useContext
    0.06
     ParseException
    0.06
    .Address
    0.06
     �
    0.06
     전문
    0.06
     Katrina
    0.06
    .:.:.:.:.:.:.:.:
    0.06
     Iterator
    0.06
    antwort
    0.06
    Act Density 0.029%

    No Known Activations