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

    Neuronpedia

    INDEX
    Explanations

    ation

    np_max-act · gemini-2.0-flash

    This neuron identifies nominalizations ending in “-ation,” especially legal terms such as “probation,” “revocation,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ,set
    -0.07
     OMIT
    -0.06
     Trek
    -0.06
    .output
    -0.06
     Hornets
    -0.06
     mouseX
    -0.06
     campos
    -0.06
    (handles
    -0.06
    .valid
    -0.06
    GraphNode
    -0.06
    POSITIVE LOGITS
    -de
    0.07
    override
    0.07
    614
    0.07
    DataAdapter
    0.07
    iov
    0.06
     B
    0.06
    209
    0.06
    Brian
    0.06
     giá
    0.06
     SECOND
    0.06
    Act Density 0.001%

    No Known Activations