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

    Neuronpedia

    INDEX
    Explanations

    Book/article excerpts

    np_max-act · gemini-2.0-flash

    The neuron detects named geographical entities and place names in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .CompilerServices
    -0.07
    .Unlock
    -0.07
    derabad
    -0.07
     期
    -0.06
     misconception
    -0.06
     conce
    -0.06
     lately
    -0.06
    Ｌ
    -0.06
    最終
    -0.06
     Arbit
    -0.06
    POSITIVE LOGITS
    Hall
    0.07
    Њ
    0.07
    "/></
    0.06
     jails
    0.06
     Hall
    0.06
     Hunter
    0.06
     Би
    0.06
     compens
    0.06
     Capability
    0.06
     일어
    0.06
    Act Density 0.051%

    No Known Activations