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

    Neuronpedia

    INDEX
    Explanations

    health and health-related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uzione
    0.43
     যাবেন
    0.42
    earch
    0.42
    ům
    0.41
    噎
    0.41
    约为
    0.40
    の開発
    0.40
     поможет
    0.39
    病毒
    0.39
    㖑
    0.39
    POSITIVE LOGITS
    iness
    0.70
     outcomes
    0.57
    ier
    0.57
     care
    0.55
    span
    0.55
    INESS
    0.54
    fulness
    0.53
    iest
    0.53
    ily
    0.52
    ish
    0.50
    Act Density 0.016%

    No Known Activations