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

    Neuronpedia

    INDEX
    Explanations

    suggestive

    np_max-act · gemini-2.0-flash

    This neuron specifically detects the special “<|start_header_id|>” token used to mark the start of a message header.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .presenter
    -0.07
    کی
    -0.07
    AH
    -0.07
    .DefaultCellStyle
    -0.07
     khỏi
    -0.07
    ESSAGE
    -0.07
    rello
    -0.07
    busy
    -0.06
    ulatory
    -0.06
     Rah
    -0.06
    POSITIVE LOGITS
    titre
    0.06
     (*)
    0.06
     अफ
    0.06
     теб
    0.06
     Restr
    0.06
    <D
    0.06
     woven
    0.06
    (ps
    0.06
    `)
    0.06
    <f
    0.06
    Act Density 0.002%

    No Known Activations