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

    Neuronpedia

    INDEX
    Explanations

    scores and maximum values

    np_max-act · gemini-2.0-flash

    The neuron does not consistently activate on any tokens and thus does not detect a specific pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    employee
    -0.07
    ну
    -0.07
    root
    -0.07
    لم
    -0.07
    더
    -0.07
     Permission
    -0.06
     blob
    -0.06
    allen
    -0.06
    gw
    -0.06
    _transport
    -0.06
    POSITIVE LOGITS
     двиг
    0.07
    (/^
    0.07
    	desc
    0.06
    ีช
    0.06
    _possible
    0.06
    Clients
    0.06
    _nama
    0.06
    _limit
    0.06
    oji
    0.06
    //----------------------------------------------------------------------------↵
    0.06
    Act Density 0.007%

    No Known Activations