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

    Neuronpedia

    INDEX
    Explanations

    a, an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Andreas
    -0.06
     WM
    -0.06
     erected
    -0.06
    经营
    -0.06
    /topics
    -0.06
    craft
    -0.06
     enth
    -0.06
     لكن
    -0.06
     ue
    -0.06
    ritable
    -0.06
    POSITIVE LOGITS
    _prediction
    0.07
     Cum
    0.06
    πουλος
    0.06
    ůže
    0.06
     Modular
    0.06
    _signup
    0.06
    _configuration
    0.06
    AttributeValue
    0.06
     commanding
    0.05
    /create
    0.05
    Act Density 0.016%

    No Known Activations