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

    Neuronpedia

    INDEX
    Explanations

    coding and debugging

    np_max-act · gemini-2.0-flash

    The neuron fires on past‐participle verbs and related file‐processing terms (e.g. “created,” “using,” “saved”) indicating how a document was generated or manipulated.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Material
    -0.07
    Father
    -0.06
    OrderBy
    -0.06
     jsonData
    -0.06
    _inc
    -0.06
     Patel
    -0.06
    Plane
    -0.06
    _sigma
    -0.06
    EEDED
    -0.06
    아
    -0.06
    POSITIVE LOGITS
     architectures
    0.06
    :{}
    0.06
     Resorts
    0.06
    $fields
    0.06
    驚
    0.06
     EPS
    0.06
    &utm
    0.06
    ária
    0.06
     Settlement
    0.06
    educated
    0.06
    Act Density 0.058%

    No Known Activations