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

    Neuronpedia

    INDEX
    Explanations

    help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (factory
    -0.07
     comeback
    -0.07
     Azure
    -0.07
     Frame
    -0.07
     fyz
    -0.07
    emphasis
    -0.07
     Simpsons
    -0.07
    NDAR
    -0.06
     vary
    -0.06
     ฉ
    -0.06
    POSITIVE LOGITS
    ı
    0.07
     minerals
    0.06
     hoses
    0.06
    Harry
    0.06
    produ
    0.06
    �a
    0.06
    OnError
    0.06
     Companies
    0.06
    ects
    0.06
     answering
    0.06
    Act Density 0.023%

    No Known Activations