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

    Neuronpedia

    INDEX
    Explanations

    News articles snippets

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of specific people’s names and other proper-name entities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bottom
    -0.07
     Carlton
    -0.06
     некоторых
    -0.06
    _VIRTUAL
    -0.06
     Bond
    -0.06
     prosecuting
    -0.06
     Rent
    -0.06
     quotations
    -0.06
    τσ
    -0.06
     Properties
    -0.06
    POSITIVE LOGITS
     لكل
    0.07
    ="{{$
    0.07
     oluyor
    0.06
    (',',
    0.06
    —who
    0.06
    csrf
    0.06
     sembl
    0.06
     ediyor
    0.06
    کنان
    0.06
    。お
    0.06
    Act Density 0.042%

    No Known Activations