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

    Neuronpedia

    INDEX
    Explanations

    delivering on promises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fermion
    0.39
     श्रमिक
    0.38
     ARISING
    0.38
     Ruhe
    0.37
     Bulb
    0.36
    ynamics
    0.35
    挿
    0.35
     EQUIPMENT
    0.34
    蛀
    0.34
     PREVENTION
    0.34
    POSITIVE LOGITS
     deliver
    1.65
     delivers
    1.55
     delivering
    1.50
    deliver
    1.42
     Delivering
    1.39
    Deliver
    1.35
     delivered
    1.34
     Deliver
    1.33
    delivered
    1.32
     entreg
    1.22
    Act Density 0.011%

    No Known Activations