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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash

    This neuron detects special metadata tokens—particularly the “<|start_header_id|>” markers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /app
    -0.08
    Brun
    -0.07
    .EndsWith
    -0.06
    Parse
    -0.06
    _defined
    -0.06
    _Syntax
    -0.06
    .Components
    -0.06
    _Context
    -0.06
    Cached
    -0.06
     Papers
    -0.06
    POSITIVE LOGITS
     debated
    0.07
     Debate
    0.06
     Alban
    0.06
     conco
    0.06
    ßerdem
    0.06
     состоя
    0.06
     debian
    0.06
     граду
    0.06
     앞
    0.06
     Connector
    0.06
    Act Density 0.110%

    No Known Activations