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

    Neuronpedia

    INDEX
    Explanations

    dund

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     movers
    -0.06
     janvier
    -0.06
     defence
    -0.06
     etmeye
    -0.06
     Advisors
    -0.06
     aspirations
    -0.06
     комнат
    -0.06
     relay
    -0.06
     Degrees
    -0.05
     tham
    -0.05
    POSITIVE LOGITS
    !!}↵
    0.08
    ῦ
    0.07
    اضي
    0.07
    esk
    0.07
    ковий
    0.07
     Accident
    0.06
    BBC
    0.06
    _disconnect
    0.06
    _completion
    0.06
    Disconnect
    0.06
    Act Density 0.001%

    No Known Activations