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

    Neuronpedia

    INDEX
    Explanations

    Establishment or recognition

    np_max-act · gemini-2.0-flash

    The neuron activates on past‐tense or historical “milestone” verbs (began, incorporated, recognized, launched, granted, etc.) that introduce events in an entity’s history.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Donald
    -0.07
    ethe
    -0.06
    ामग
    -0.06
     retorna
    -0.06
    species
    -0.06
    adors
    -0.06
    ูน
    -0.06
    غط
    -0.06
    358
    -0.06
     dataSet
    -0.06
    POSITIVE LOGITS
    Guardar
    0.07
    (images
    0.06
     яку
    0.06
     Birds
    0.06
    正确
    0.06
     od
    0.06
    ]bool
    0.06
    **/↵
    0.06
     elections
    0.06
    �
    0.06
    Act Density 0.146%

    No Known Activations