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

    Neuronpedia

    INDEX
    Explanations

    creates positive outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    │
    0.69
     or
    0.67
    あるいは
    0.61
    question
    0.61
    --------
    0.60
    ways
    0.57
    ________
    0.57
     affairs
    0.57
     أو
    0.56
    ----
    0.56
    POSITIVE LOGITS
     momentum
    1.01
     accountability
    0.99
     credibility
    0.96
    continuity
    0.93
     continuity
    0.92
     visualiser
    0.88
     consistency
    0.88
     legitimacy
    0.88
     inertia
    0.86
     freshness
    0.86
    Act Density 1.470%

    No Known Activations